© 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. 67288
    Prev
    Next
    INDEX
    Explanations

    any more

    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
    ⢅
    -1.99
    罴
    -1.98
    をしています
    -1.97
    猡
    -1.93
    谨慎
    -1.88
    蚰
    -1.88
    镡
    -1.87
     แต่
    -1.86
     wes
    -1.84
    凩
    -1.84
    POSITIVE LOGITS
     of
    2.88
     or
    2.17
    r
    2.00
    '
    1.92
     â
    1.77
    夏天
    1.69
     meiner
    1.67
     they
    1.67
     '
    1.66
    dzić
    1.63
    Activations Density 0.006%

    No Known Activations