© 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. 44634
    Prev
    Next
    INDEX
    Explanations

    html head 8

    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
     virtudes
    -2.28
    䊊
    -2.25
    蕻
    -2.05
    
    -1.98
    ௜
    -1.93
    schon
    -1.92
    re
    -1.92
    Vaya
    -1.90
    
    -1.87
     撮り
    -1.86
    POSITIVE LOGITS
    .
    3.09
    If
    2.56
    There
    2.14
    They
    1.93
     time
    1.88
     will
    1.84
     same
    1.84
    多かった
    1.83
    chläge
    1.83
     This
    1.80
    Activations Density 0.017%

    No Known Activations