© 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. 2085
    Prev
    Next
    INDEX
    Explanations

    distance and numerical examples

    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
     overfitting
    0.36
     carcinogenesis
    0.34
    😧
    0.31
     arthrop
    0.31
     astrophysical
    0.30
     rulemaking
    0.30
     antigens
    0.30
     pandemics
    0.30
     geniuses
    0.30
     savages
    0.30
    POSITIVE LOGITS
     Y
    0.40
     H
    0.39
     M
    0.36
     S
    0.35
     R
    0.34
     N
    0.34
     D
    0.34
     G
    0.34
     P
    0.33
     F
    0.32
    Activations Density 2.134%

    No Known Activations