© 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. 118857
    Prev
    Next
    INDEX
    Explanations

    import statements and paths

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

    the keyword "import" in code files (especially in import statements across various programming languages and configuration files).

    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
    }$
    -2.48
    D
    -2.31
    ↵↵
    -2.11
    m
    -2.05
     It
    -1.98
    C
    -1.95
    begin
    -1.88
    ;
    -1.86
    ia
    -1.84
    Such
    -1.84
    POSITIVE LOGITS
    摃
    2.52
     juſ
    2.09
    瘣
    2.08
    卺
    2.06
     récentes
    2.06
    豨
    2.02
    ⛦
    2.02
    趼
    1.91
     setPrice
    1.88
    鳚
    1.86
    Activations Density 0.014%

    No Known Activations