© 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. 15253
    Prev
    Next
    INDEX
    Explanations

    scripting and code languages

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     unſ
    -2.44
    ⢊
    -2.20
    s
    -2.20
    
    -1.96
     them
    -1.92
    ization
    -1.91
     fidé
    -1.88
     hanno
    -1.85
     They
    -1.84
    翆
    -1.83
    POSITIVE LOGITS
     was
    2.30
     has
    1.96
    apatalk
    1.95
    mga
    1.94
     verbess
    1.93
     может
    1.88
     extensive
    1.78
    '
    1.71
     will
    1.70
    Script
    1.70
    Activations Density 0.009%

    No Known Activations