© 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. 10-GEMMASCOPE-RES-131K
    7. 119610
    Prev
    Next
    INDEX
    Explanations

    academic or year citations

    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
     cikk
    -1.67
     nhau
    -1.62
     themselves
    -1.53
     pamoja
    -1.47
    crema
    -1.39
    琺
    -1.39
     jöv
    -1.38
     szép
    -1.38
     eszköz
    -1.38
     legjobb
    -1.36
    POSITIVE LOGITS
     there
    1.66
     its
    1.55
    There
    1.38
     himself
    1.31
     if
    1.29
    tvrt
    1.25
    %
    1.23
    6
    1.21
     always
    1.19
     or
    1.16
    Activations Density 0.032%

    No Known Activations