© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1861
    Prev
    Next
    INDEX
    Explanations

    static analysis and best practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ς
    0.55
    𝓷
    0.52
    érrez
    0.52
    ᵢ
    0.48
    ęła
    0.48
     terapi
    0.47
     AppBsky
    0.46
    ফোঁ
    0.46
    _.
    0.46
     partielle
    0.46
    POSITIVE LOGITS
    Reviewed
    0.54
     threat
    0.49
     based
    0.49
     best
    0.48
    Straw
    0.45
    Worst
    0.45
     wheat
    0.44
     coming
    0.44
     تهد
    0.43
    ಿಕೆ
    0.42
    Activations Density 0.001%

    No Known Activations