© 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. 67228
    Prev
    Next
    INDEX
    Explanations

    how much

    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
     短发
    -2.03
    魔兽
    -1.99
    Приготовление
    -1.98
     炖
    -1.98
     帅气
    -1.96
    蒟
    -1.95
    目次
    -1.95
    梅雨
    -1.92
    蠵
    -1.91
     videa
    -1.84
    POSITIVE LOGITS
    s
    2.33
    p
    2.14
    んだり
    2.00
     \
    1.94
     was
    1.83
    which
    1.75
    n
    1.75
     enam
    1.75
    lo
    1.73
    um
    1.73
    Activations Density 0.017%

    No Known Activations