© 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. 73199
    Prev
    Next
    INDEX
    Explanations

    documentation and code examples

    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
     This
    -1.86
    หรือ
    -1.86
    戮
    -1.81
     by
    -1.77
     Previously
    -1.77
    pernicus
    -1.77
     Ultimately
    -1.77
    4
    -1.75
     Altogether
    -1.75
    痢
    -1.73
    POSITIVE LOGITS
    
    2.09
    榦
    2.08
    儅
    2.02
     inaugu
    1.97
    냑
    1.96
     consag
    1.95
    ㊃
    1.94
    着一个
    1.91
     inaugura
    1.89
     流れ
    1.89
    Activations Density 0.001%

    No Known Activations