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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10189
    Prev
    Next
    INDEX
    Explanations

    round shapes and descriptions

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

    The neuron responds to capitalized words that are proper names or titles (i.e., named entities).

    oai_token-act-pair · o4-miniTriggered 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
    向き
    0.65
    NAMEN
    0.64
     rapporte
    0.63
    㝌
    0.63
    常に
    0.63
    GEBURTS
    0.63
    その
    0.62
     videot
    0.61
    VERTISE
    0.61
    敔
    0.60
    POSITIVE LOGITS
    being
    0.72
    ą
    0.70
    東西
    0.68
    limb
    0.66
     avoiding
    0.64
     চোখ
    0.64
     Beyond
    0.64
    yang
    0.64
     কাউকে
    0.63
    Beyond
    0.63
    Activations Density 0.000%

    No Known Activations