© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176987
    Prev
    Next
    INDEX
    Explanations

    foreign characters or symbols

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

    honor and Trust

    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
    Negative Logits
    la
    0.47
    くらいの
    0.44
    赌
    0.42
    ု
    0.41
    賭
    0.41
    隨
    0.40
    лює
    0.40
     suspicion
    0.38
     patt
    0.38
    де
    0.38
    POSITIVE LOGITS
     ∆
    0.54
    AreaData
    0.50
    ❆
    0.50
    🔋
    0.49
    🥫
    0.49
    აცია
    0.49
     уйнарга
    0.48
    వృద్ధి
    0.46
     எடுத்துக்கா
    0.46
    🕍
    0.46
    Activations Density 0.001%

    No Known Activations