© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6251
    Prev
    Next
    INDEX
    Explanations

    main method signature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     the
    0.76
     "
    0.63
     =
    0.61
    ")
    0.61
     void
    0.58
     auto
    0.57
     beep
    0.57
    ");
    0.57
    the
    0.57
     boolean
    0.56
    POSITIVE LOGITS
    ennials
    0.84
     अय्यर
    0.74
    giants
    0.74
    juvant
    0.73
     يوم
    0.73
    pectives
    0.73
    곁
    0.73
    apeake
    0.72
     今天
    0.71
    Más
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.