© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20905
    Prev
    Next
    INDEX
    Explanations

    names of lists

    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
     who
    -1.57
    FUNCTION
    -1.55
    href
    -1.55
    amica
    -1.52
     your
    -1.50
     Meille
    -1.48
    ᯾
    -1.48
    ֟
    -1.48
    ㋛
    -1.48
    garve
    -1.45
    POSITIVE LOGITS
    檩
    1.38
    ↵
    1.38
    viembre
    1.24
    أك
    1.20
    шники
    1.17
    複数
    1.16
    地说
    1.15
    贽
    1.15
    荣誉
    1.14
    Conjunto
    1.14
    Activations Density 0.070%

    No Known Activations