© 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. 44674
    Prev
    Next
    INDEX
    Explanations

    grid size, complexity, culture, trigger

    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
    ஓ
    0.55
    ध्या
    0.50
    .|__
    0.50
     baya
    0.50
    不過
    0.48
    انا
    0.47
    ကြာ
    0.47
     ignor
    0.47
     są
    0.46
     ஆனால்
    0.46
    POSITIVE LOGITS
    0.46
    z
    0.44
    更多
    0.40
    id
    0.39
    Comple
    0.38
    0.38
    äche
    0.37
    Formula
    0.37
     rapporto
    0.37
     timestamp
    0.36
    Activations Density 0.001%

    No Known Activations