© 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. 100116
    Prev
    Next
    INDEX
    Explanations

    semicolon comments and keywords

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

    semicolons that appear at the beginning of lines in code or 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
     exclusively
    -2.17
    ….
    -2.16
    𓆜
    -2.05
     キャンペーン
    -2.03
     guarantee
    -1.99
     coupled
    -1.96
    见状
    -1.96
     науки
    -1.95
    on
    -1.95
     aptly
    -1.94
    POSITIVE LOGITS
    颪
    2.36
     rivales
    2.20
     naturels
    2.20
    
    2.09
    矬
    2.08
    ("
    2.08
     étage
    2.06
    咙
    2.03
     création
    1.98
    螃
    1.98
    Activations Density 0.021%

    No Known Activations