© 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. 1529
    Prev
    Next
    INDEX
    Explanations

    CSS selectors and script tags

    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
    ৄ
    -1.69
     then
    -1.54
     என்ப
    -1.51
    驺
    -1.51
    鉿
    -1.50
     cristianismo
    -1.50
     枚
    -1.49
    liebe
    -1.48
     years
    -1.47
     to
    -1.46
    POSITIVE LOGITS
    While
    1.58
    n
    1.57
    s
    1.51
    <
    1.43
    1.42
    r
    1.41
    ところが
    1.36
    1.35
    <blockquote>
    1.34
    D
    1.34
    Activations Density 0.017%
    No Known Activations