© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191320
    Prev
    Next
    INDEX
    Explanations

    electric car models and specs

    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_40_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
     ड्रिल
    0.47
     Drilling
    0.44
    蜒
    0.40
     Drill
    0.40
    鑽
    0.39
     drill
    0.39
     Boley
    0.38
     Healey
    0.38
     Brum
    0.37
     hydrocarbons
    0.37
    POSITIVE LOGITS
    сию
    0.41
     react
    0.41
     shifts
    0.40
    стере
    0.40
     specificity
    0.38
    react
    0.38
     NBC
    0.38
     ≤
    0.37
    asche
    0.37
    src
    0.36
    Activations Density 0.005%

    No Known Activations