© 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. 10-GEMMASCOPE-RES-131K
    7. 615
    Prev
    Next
    INDEX
    Explanations

    working correctly or not

    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
     only
    -1.70
     but
    -1.66
     тільки
    -1.45
     лише
    -1.38
    only
    -1.37
     Only
    -1.23
     فقط
    -1.20
    Only
    -1.18
     только
    -1.13
    只有
    -1.13
    POSITIVE LOGITS
     honom
    1.38
     weiteres
    1.33
    Törté
    1.32
     juiz
    1.23
     également
    1.22
     schönes
    1.20
     jego
    1.20
     where
    1.17
     esconder
    1.17
    ernsey
    1.16
    Activations Density 0.211%

    No Known Activations