© 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. 21182
    Prev
    Next
    INDEX
    Explanations

    The incident, offences, diocese, partnership, court, cameras

    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
     Since
    -2.53
     in
    -2.39
     all
    -2.28
     If
    -2.28
     While
    -2.27
     During
    -2.20
     to
    -2.16
     or
    -2.09
     will
    -2.09
     Many
    -2.06
    POSITIVE LOGITS
     этого
    2.02
    雠
    1.98
     этом
    1.98
     zoude
    1.95
    
    1.93
    ↵
    1.91
    
    1.91
     сына
    1.89
    Ｚ
    1.88
    饜
    1.82
    Activations Density 0.252%

    No Known Activations