© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12375
    Prev
    Next
    INDEX
    Explanations

    dates back to origins

    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_22/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
     this
    -1.69
     and
    -1.48
     will
    -1.47
     each
    -1.45
     everything
    -1.22
     more
    -1.21
     without
    -1.19
    ַּ
    -1.16
    gering
    -1.16
     has
    -1.16
    POSITIVE LOGITS
     chré
    1.45
     religieuses
    1.41
     religieux
    1.34
    ׇ
    1.33
    Étape
    1.25
     keş
    1.23
    我才
    1.22
     perú
    1.21
     kimse
    1.20
    ФИ
    1.18
    Activations Density 0.073%

    No Known Activations