© 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. 34-GEMMASCOPE-RES-131K
    4. 77092
    Prev
    Next
    INDEX
    Explanations

    all followed by a quantity

    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_34/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
     которому
    -1.15
     mainly
    -1.02
     really
    -1.02
     actually
    -1.02
     constantly
    -0.98
     even
    -0.97
     mostly
    -0.97
     which
    -0.97
     in
    -0.96
    𝗮
    -0.96
    POSITIVE LOGITS
     three
    1.93
     four
    1.73
     but
    1.62
     five
    1.59
     of
    1.46
     two
    1.34
     eight
    1.30
     six
    1.28
    three
    1.27
     seven
    1.26
    Activations Density 0.042%

    No Known Activations