© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129198
    Prev
    Next
    INDEX
    Explanations

    state or situation

    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
    踉
    -1.75
    惴
    -1.56
    ってみました
    -1.55
    がこの
    -1.53
    を書く
    -1.47
    vertebrate
    -1.46
    tissimo
    -1.45
     இந்த
    -1.44
     who
    -1.44
    絝
    -1.43
    POSITIVE LOGITS
     of
    2.09
     at
    1.83
     for
    1.73
     to
    1.68
     what
    1.66
     Ayrıca
    1.62
     had
    1.59
    .}(
    1.49
     or
    1.45
     before
    1.45
    Activations Density 20.045%

    No Known Activations