© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11533
    Prev
    Next
    INDEX
    Explanations

    website or media sources

    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
     already
    -1.47
    +#+
    -1.42
     GRAHAM
    -1.41
    酵素
    -1.37
    ൨
    -1.34
     będziemy
    -1.33
    commod
    -1.29
    やろ
    -1.27
    :+:
    -1.27
     his
    -1.27
    POSITIVE LOGITS
     that
    2.50
     which
    1.80
     (
    1.65
     of
    1.52
     about
    1.52
     That
    1.49
     When
    1.45
     often
    1.44
     these
    1.42
     those
    1.34
    Activations Density 0.259%

    No Known Activations