© 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. 61227
    Prev
    Next
    INDEX
    Explanations

    responsible for producing

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

    role in

    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
    н
    0.66
    к
    0.57
    aryng
    0.49
    ethe
    0.48
    ittle
    0.47
    tsy
    0.47
    such
    0.47
    绞
    0.46
    kap
    0.46
    ocker
    0.46
    POSITIVE LOGITS
     auton
    0.55
    -
    0.48
     giornata
    0.48
     divaric
    0.47
     windows
    0.47
     projected
    0.47
     projectors
    0.47
     cnv
    0.46
     tailgate
    0.46
     KIR
    0.46
    Activations Density 0.000%

    No Known Activations