© 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. 67687
    Prev
    Next
    INDEX
    Explanations

    until a state

    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
     of
    -2.19
     $
    -1.91
    0
    -1.59
     (>
    -1.50
    没人
    -1.49
    注定
    -1.49
    '
    -1.48
    5
    -1.48
    3
    -1.48
     mutta
    -1.47
    POSITIVE LOGITS
    
    1.86
    鲞
    1.77
     deudas
    1.72
    垆
    1.71
    </strong>
    1.71
    奩
    1.71
     époux
    1.69
     quitté
    1.68
     unſ
    1.67
    ি
    1.65
    Activations Density 0.010%

    No Known Activations