© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7083
    Prev
    Next
    INDEX
    Explanations

    Victims, captivating, moderation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     Provident
    1.82
     Redistributions
    1.77
    қан
    1.76
     vaya
    1.73
     "-//
    1.73
     yì
    1.72
     ใด
    1.71
    discard
    1.63
    acağını
    1.63
    besondere
    1.63
    POSITIVE LOGITS
    adilan
    1.65
    inguistic
    1.58
    itable
    1.57
    UNIC
    1.54
    狈
    1.48
     unique
    1.48
    esso
    1.48
    ynyl
    1.43
    otiv
    1.43
    undo
    1.42
    Activations Density 0.238%

    No Known Activations