© 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. 14507
    Prev
    Next
    INDEX
    Explanations

    look at, up, out, back, forward

    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
    梣
    -2.19
    蹩
    -2.05
     時尚
    -2.05
    沨
    -2.03
    AddHtmlAttribute
    -1.98
    啰
    -1.98
    戏剧
    -1.96
    Ꮉ
    -1.93
    gencias
    -1.91
     wireType
    -1.91
    POSITIVE LOGITS
    '
    2.03
     ???
    1.88
    ks
    1.84
     oder
    1.84
    鉆
    1.79
     testament
    1.77
    look
    1.70
     out
    1.70
    ان
    1.69
    ie
    1.67
    Activations Density 0.038%

    No Known Activations