© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100004
    Prev
    Next
    INDEX
    Explanations

    database transaction or save

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

    method calls or function invocations that end with parentheses, particularly in programming code.

    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
    ＋
    -2.58
    
    -2.42
    ＆
    -2.39
     знали
    -2.34
     khỏ
    -2.34
    灕
    -2.31
     ！
    -2.27
     '
    -2.23
     dotyczące
    -2.22
    ...'
    -2.20
    POSITIVE LOGITS
     they
    3.08
     was
    2.33
    ↵
    2.31
    轳
    2.30
     Of
    2.16
     told
    2.02
    x
    1.95
    ของ
    1.91
    يل
    1.91
    u
    1.88
    Activations Density 0.000%

    No Known Activations