© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10840
    Prev
    Next
    INDEX
    Explanations

    Slavic languages, programming contexts

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

    pronouns and demonstrative words in Slavic languages (particularly Russian, Polish, and Czech).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     is
    -1.88
     недавно
    -1.84
    .
    -1.81
     głównie
    -1.63
    ↵
    -1.61
     cuando
    -1.59
    没办法
    -1.57
    就没
    -1.54
    */
    -1.52
     aliviar
    -1.50
    POSITIVE LOGITS
     bahkan
    1.87
     also
    1.73
     variation
    1.67
     zgod
    1.60
    СЫ
    1.58
    "—
    1.57
     beserta
    1.56
    tisgarh
    1.53
     diantaranya
    1.50
    (
    1.46
    Activations Density 0.003%

    No Known Activations