© 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. 13609
    Prev
    Next
    INDEX
    Explanations

    lists, selectors, or properties

    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
    を提供
    0.52
     Barrios
    0.45
    <<
    0.43
     Grundlage
    0.42
     Aro
    0.42
    Из
    0.40
    ل
    0.40
     Buss
    0.40
    STY
    0.40
     Lant
    0.39
    POSITIVE LOGITS
     summoning
    0.45
     perfettamente
    0.44
     비슷한
    0.44
     perfectly
    0.43
     អ្នក
    0.43
     ე
    0.42
    watering
    0.42
     loosening
    0.42
    őbb
    0.41
     justo
    0.41
    Activations Density 0.001%

    No Known Activations