© 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. 28035
    Prev
    Next
    INDEX
    Explanations

    dress code and versioning

    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
    Families
    0.50
    AED
    0.47
    foils
    0.47
    Bub
    0.46
    Attorney
    0.46
    Senior
    0.45
    a
    0.44
    s
    0.44
    ي
    0.44
    Hib
    0.44
    POSITIVE LOGITS
     சுற்று
    0.49
     typewriter
    0.48
    ніше
    0.47
     pâte
    0.46
     cobbl
    0.45
     overnight
    0.45
     tipping
    0.45
     vše
    0.44
    ivität
    0.44
     climbed
    0.44
    Activations Density 0.006%

    No Known Activations