© 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. 13984
    Prev
    Next
    INDEX
    Explanations

    linkinglinked ids and objects

    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
    ↵
    -2.00
     “
    -1.77
    s
    -1.77
     (“
    -1.74
    t
    -1.59
    p
    -1.53
    es
    -1.52
    ’.
    -1.51
    ’
    -1.50
    </strong>
    -1.46
    POSITIVE LOGITS
     Conſ
    2.33
     Reſ
    2.19
    trás
    1.95
     trám
    1.88
     Diſ
    1.88
    婓
    1.84
    
    1.84
     citoy
    1.79
    小孩子
    1.77
    ゎ
    1.77
    Activations Density 0.022%

    No Known Activations