© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6379
    Prev
    Next
    INDEX
    Explanations

    brings you and was your

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

    This neuron strongly activates on words relating to collecting or asking for people’s personal or demographic information (e.g. age, year born, visitor status, policy compliance).

    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
    <unused2164>
    1.09
    <unused2172>
    0.93
    <unused2125>
    0.88
    <unused2221>
    0.86
    𝐂
    0.82
    <unused2126>
    0.81
    <unused2231>
    0.81
     २०२
    0.80
    <unused2130>
    0.79
    <unused2206>
    0.75
    POSITIVE LOGITS
     shenanigans
    1.63
     monstros
    1.49
     behem
    1.47
     hapless
    1.43
     trusty
    1.33
     goodies
    1.32
     pesky
    1.28
     antics
    1.27
     hideous
    1.25
     stupidity
    1.25
    Activations Density 1.947%

    No Known Activations