© 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. 102333
    Prev
    Next
    INDEX
    Explanations

    comparisons of scale and traits

    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
    EIN
    0.58
    IFORNIA
    0.50
    a
    0.49
    h
    0.49
    硫
    0.48
    VOL
    0.47
    znych
    0.46
    孜
    0.46
    ECTION
    0.46
    v
    0.46
    POSITIVE LOGITS
     risque
    0.47
     Horm
    0.46
     Ribeiro
    0.46
     are
    0.46
     bloque
    0.46
     detour
    0.46
     neutralize
    0.45
     change
    0.45
     indique
    0.45
     to
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.