© 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. 113407
    Prev
    Next
    INDEX
    Explanations

    boolean values or verification

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

    newline or whitespace characters that separate lines or sections of structured text.

    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
     frequentemente
    -2.02
    莇
    -1.87
    '){
    -1.80
     vorhand
    -1.78
    
    -1.75
     spezi
    -1.71
     někter
    -1.71
    
    -1.70
     }}{
    -1.70
     häufiger
    -1.68
    POSITIVE LOGITS
     or
    2.52
    :
    2.19
     at
    2.17
     in
    1.99
    \
    1.94
     will
    1.89
     it
    1.85
    },
    1.77
     all
    1.77
     which
    1.68
    Activations Density 0.048%

    No Known Activations