© 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. 28657
    Prev
    Next
    INDEX
    Explanations

    geographical names

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

    regions, countries, nationalities

    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
     आईसीआर
    0.52
    质疑
    0.52
    MaxScaler
    0.51
    EnglishMarks
    0.51
     فونبټ
    0.50
     ఆరోగ్య
    0.49
    OpportunitiesBy
    0.49
    睗
    0.49
     감소
    0.49
    StockDel
    0.48
    POSITIVE LOGITS
     P
    0.65
     (
    0.63
     are
    0.63
     S
    0.62
     L
    0.56
     and
    0.55
    0.55
     D
    0.54
     são
    0.53
     C
    0.52
    Activations Density 0.006%

    No Known Activations