© 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. 84905
    Prev
    Next
    INDEX
    Explanations

    event handling and specific technical terms

    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
    тся
    -2.56
     They
    -2.56
    t
    -2.48
     شما
    -2.41
    as
    -2.33
    на
    -2.30
     If
    -2.27
    抨
    -2.23
    枷
    -2.19
    双方
    -2.16
    POSITIVE LOGITS
    铪
    2.52
    ཫ
    2.47
    葑
    2.47
    祧
    2.44
    葙
    2.44
     jaką
    2.42
    းက
    2.41
     parachoque
    2.25
    ㈲
    2.25
    囖
    2.22
    Activations Density 0.001%

    No Known Activations