© 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. 36654
    Prev
    Next
    INDEX
    Explanations

    actions and commands

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

    code execution of commands

    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
    olian
    0.52
     Reilly
    0.51
     Lyle
    0.51
    elier
    0.50
     Hickey
    0.50
     Malcolm
    0.49
     伊
    0.49
    oking
    0.49
     Atty
    0.48
    czna
    0.48
    POSITIVE LOGITS
    ();
    0.56
     dosages
    0.50
     causando
    0.48
    (',');
    0.46
     diventa
    0.45
     probabilidad
    0.45
     intentos
    0.44
     esfuerzos
    0.43
     partidas
    0.43
    ;
    0.43
    Activations Density 0.000%

    No Known Activations