© 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. 667
    Prev
    Next
    INDEX
    Explanations

    people's actions, values, and experiences

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

    The neuron responds to rare, informational content words (e.g. named entities and technical nouns) rather than common function words.

    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
    f
    0.63
    r
    0.57
    c
    0.56
    ）、
    0.55
    ="")
    0.55
    v
    0.53
    xsi
    0.53
    etc
    0.52
    method
    0.52
    竣
    0.51
    POSITIVE LOGITS
     minds
    0.98
     hearts
    0.94
     psyche
    0.89
     sensibilities
    0.88
     Bedürfnisse
    0.88
     perceptions
    0.86
     lives
    0.85
     opinions
    0.84
     citizenry
    0.83
     emberek
    0.82
    Activations Density 0.366%

    No Known Activations