© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14168
    Prev
    Next
    INDEX
    Explanations

    winning combinations, teams, or records

    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
     '
    -3.81
    (
    -3.52
    \
    -3.06
    *
    -3.03
    {
    -2.97
     {
    -2.92
    e
    -2.70
    “
    -2.55
    —
    -2.52
    am
    -2.41
    POSITIVE LOGITS
    姈
    3.48
    鋮
    3.28
    鸶
    3.27
    弍
    3.02
    Ꭳ
    2.89
    酲
    2.84
    趼
    2.70
    utterstock
    2.67
    欵
    2.67
    ائومی
    2.63
    Activations Density 0.004%

    No Known Activations