© 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. 67883
    Prev
    Next
    INDEX
    Explanations

    import statements and code identifiers

    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
    耷
    -1.75
    
    -1.74
    苜
    -1.72
    ใน
    -1.57
     její
    -1.57
    惴
    -1.55
     её
    -1.55
     ventes
    -1.55
     psychologie
    -1.55
     ſou
    -1.54
    POSITIVE LOGITS
     all
    2.61
     any
    2.13
     everything
    2.03
     each
    2.02
     not
    1.98
     using
    1.97
     the
    1.97
     their
    1.93
     some
    1.89
     just
    1.86
    Activations Density 0.199%

    No Known Activations