© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101977
    Prev
    Next
    INDEX
    Explanations

    user-defined literals

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

    empty strings in code (represented by `""`).

    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
    鹋
    -3.53
    橚
    -2.97
     современных
    -2.67
    ȹ
    -2.66
    鹮
    -2.63
    彞
    -2.63
    tedì
    -2.61
    
    -2.59
    ྵ
    -2.50
    崐
    -2.50
    POSITIVE LOGITS
    e
    2.97
    ти
    2.83
    ка
    2.53
    ization
    2.44
    '__
    2.34
    v
    2.34
    ان
    2.31
    an
    2.31
    孓
    2.30
    in
    2.28
    Activations Density 0.003%

    No Known Activations