© 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. 9602
    Prev
    Next
    INDEX
    Explanations

    code or parameter values

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

    if, else, or for

    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
    鉆
    0.44
    ROBERT
    0.43
    tahun
    0.43
     Букмекердик
    0.42
    CHRIST
    0.42
    tempat
    0.41
     Букмекерлер
    0.41
    dört
    0.40
    他說
    0.40
    LORD
    0.40
    POSITIVE LOGITS
     else
    0.52
     ("
    0.52
    .
    0.51
    -
    0.48
     Else
    0.47
     (
    0.46
    ;
    0.45
    +
    0.45
    *
    0.45
     (“
    0.44
    Activations Density 0.015%

    No Known Activations