© 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. 90651
    Prev
    Next
    INDEX
    Explanations

    specific listed names or works

    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
    ꒥
    -1.37
    Karakteristik
    -1.34
     mostrare
    -1.34
     produrre
    -1.30
    л
    -1.28
    Kelebihan
    -1.28
    aned
    -1.28
    aried
    -1.27
    or
    -1.27
    ITIONS
    -1.27
    POSITIVE LOGITS
    :
    2.06
     both
    1.69
    '
    1.63
    </h1>
    1.54
    </strong>
    1.41
     to
    1.40
     of
    1.38
    )){
    1.34
    (
    1.30
    eclamp
    1.28
    Activations Density 0.056%

    No Known Activations