© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67554
    Prev
    Next
    INDEX
    Explanations

    new things discovered

    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_22/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
     to
    -1.27
    ྂ
    -1.26
    -
    -1.26
    cete
    -1.18
     aukš
    -1.17
    ಠ
    -1.11
    𝑥
    -1.10
    粜
    -1.09
    撵
    -1.09
     vœ
    -1.07
    POSITIVE LOGITS
     areas
    1.43
     ways
    1.39
     those
    1.37
     hogyan
    1.36
     seldom
    1.32
    ALLENG
    1.27
     new
    1.27
     things
    1.26
    ípios
    1.26
     possibilities
    1.23
    Activations Density 0.031%

    No Known Activations