© 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. 55071
    Prev
    Next
    INDEX
    Explanations

    personal preferences

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

    phonetic puns and calculator tricks

    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
     Na
    0.50
    W
    0.46
    replica
    0.45
     liu
    0.45
    s
    0.44
    re
    0.43
    枴
    0.43
     stimulus
    0.42
     ie
    0.42
     Hu
    0.42
    POSITIVE LOGITS
    ждый
    0.49
    assadors
    0.48
    ắp
    0.47
     чыныгы
    0.46
    噜
    0.45
    SrvGroup
    0.45
    荤
    0.44
    룹
    0.44
    낍
    0.44
     comfortably
    0.44
    Activations Density 0.000%

    No Known Activations