© 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. 10264
    Prev
    Next
    INDEX
    Explanations

    history, application, and elderly

    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
     the
    -1.63
     verhind
    -1.54
    ┫
    -1.40
     första
    -1.39
    kopi
    -1.35
    蓐
    -1.35
    guisement
    -1.34
     rigue
    -1.32
    ಅ
    -1.32
    ок
    -1.31
    POSITIVE LOGITS
     of
    1.95
     as
    1.55
     to
    1.47
     —
    1.46
     those
    1.45
    Those
    1.45
     mostly
    1.41
     when
    1.40
     (
    1.39
    m
    1.38
    Activations Density 0.140%

    No Known Activations