© 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. 87275
    Prev
    Next
    INDEX
    Explanations

    sawn lumber, savers, saxes

    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
    獁
    -3.25
    quelize
    -2.95
    ⬮
    -2.86
     baumwolle
    -2.61
     CALIFOR
    -2.58
     科技
    -2.53
    酆
    -2.50
    茕
    -2.48
    遄
    -2.45
    ➄
    -2.44
    POSITIVE LOGITS
    ?
    3.36
    {
    3.14
    --
    3.11
    焔
    2.80
    =
    2.69
    (
    2.67
    ".
    2.55
     `
    2.55
    jenige
    2.48
     zumal
    2.45
    Activations Density 0.004%

    No Known Activations