© 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. 12773
    Prev
    Next
    INDEX
    Explanations

    Core Data objects

    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
     vin
    0.50
     ảo
    0.50
     heal
    0.50
     hỗ
    0.50
     an
    0.49
     change
    0.49
     evolve
    0.48
    ח
    0.48
     reinforce
    0.48
     excessive
    0.47
    POSITIVE LOGITS
    iejs
    0.47
    ństwa
    0.47
    ئی
    0.46
    ophila
    0.46
    inės
    0.46
     Investigations
    0.45
    iew
    0.45
    ัตว์
    0.44
    byterian
    0.44
    ettha
    0.43
    Activations Density 0.001%

    No Known Activations