© 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. 41478
    Prev
    Next
    INDEX
    Explanations

    explaining concepts or guidance

    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
     промышленности
    0.44
    ০০০
    0.41
    ራ
    0.41
     ماشینونو
    0.40
    రావు
    0.38
     প্রাধ
    0.38
    κή
    0.38
     Standing
    0.38
     Prav
    0.37
    ровано
    0.37
    POSITIVE LOGITS
    src
    0.51
    df
    0.46
    का
    0.45
    ㄈ
    0.44
    adients
    0.44
     end
    0.44
    GES
    0.44
    dirs
    0.44
     outlier
    0.43
     aDict
    0.43
    Activations Density 0.004%

    No Known Activations