© 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. 19418
    Prev
    Next
    INDEX
    Explanations

    managed followed by noun

    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
    簠
    -2.91
    ⢌
    -2.84
    ᷆
    -2.69
    籥
    -2.64
    癰
    -2.59
    甞
    -2.58
    皤
    -2.53
     we
    -2.53
    螣
    -2.52
    癭
    -2.47
    POSITIVE LOGITS
    This
    3.55
    -
    3.50
     For
    3.00
    .
    2.84
    `
    2.70
    These
    2.67
     =
    2.66
    m
    2.64
    </h3>
    2.52
    ?
    2.52
    Activations Density 0.005%

    No Known Activations