© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74370
    Prev
    Next
    INDEX
    Explanations

    don't miss out

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

    entity definition, function block, model file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Melitaea
    0.47
    ParamNum
    0.41
    inherit
    0.41
     resembles
    0.40
    ínez
    0.40
    됨
    0.40
    Regards
    0.39
    न्हा
    0.38
     avoids
    0.38
    Separate
    0.38
    POSITIVE LOGITS
     ಕರೆ
    0.44
     Sprou
    0.44
    った
    0.43
    tà
    0.42
    CTR
    0.42
    пар
    0.42
    ской
    0.41
    ቋ
    0.41
    this
    0.41
    사와
    0.41
    Activations Density 0.000%

    No Known Activations