© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8189
    Prev
    Next
    INDEX
    Explanations

    self-narrative, architect of identity

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on words referring to urban environments and public‐space contexts (e.g., city, street, subway, market, realm).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    analytical or formal academic writing, particularly comparative discussions of societies, systems, or institutions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions of urban environments and civic infrastructure, especially public space use, governance, and transportation in cities.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     거예요
    1.31
     돼요
    1.27
     있어요
    1.15
     разные
    1.12
    すごく
    1.12
    いろんな
    1.09
    㗎
    1.09
     sooo
    1.06
     엄마
    1.06
    だけど
    1.05
    POSITIVE LOGITS
     skall
    1.18
     recieved
    1.18
     recieve
    1.02
    にて
    0.99
    recieve
    0.93
     אשר
    0.93
    更に
    0.88
    へと
    0.88
     extant
    0.87
     whilst
    0.86
    Activations Density 0.633%

    No Known Activations