© 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. 71113
    Prev
    Next
    INDEX
    Explanations

    names and their contexts

    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
    数量
    -2.52
    </h3>
    -2.27
     車場
    -2.25
    même
    -2.19
    mería
    -2.13
     肖像
    -2.11
     Là
    -2.11
    ma
    -2.08
    "../
    -2.08
    of
    -2.06
    POSITIVE LOGITS
    </b>
    3.42
    ing
    2.56
    ⚋
    2.41
     [
    2.34
    趼
    2.33
     the
    2.27
    that
    2.27
     It
    2.25
     MUCH
    2.20
     Bemerkungen
    2.20
    Activations Density 0.012%

    No Known Activations