© 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-262K
    7. 200323
    Prev
    Next
    INDEX
    Explanations

    biological and technical lists

    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_262k_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
     (=
    0.57
     objected
    0.56
     protested
    0.52
     vigorously
    0.50
     irrigated
    0.50
     ইরান
    0.50
    recer
    0.49
     denounced
    0.49
    ット
    0.49
     diverted
    0.49
    POSITIVE LOGITS
     Configurations
    0.49
     Simple
    0.48
     Silent
    0.44
    W
    0.44
     Performance
    0.42
    L
    0.42
     Relationship
    0.41
    Simple
    0.41
    \*
    0.41
    G
    0.41
    Activations Density 0.005%

    No Known Activations