© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76284
    Prev
    Next
    INDEX
    Explanations

    describing actions and states

    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
    苳
    0.50
    రించ
    0.48
     オレンジ
    0.46
    鎊
    0.46
    병원
    0.45
    醫生
    0.45
    GetOffset
    0.45
    糉
    0.45
     হাসপাত
    0.44
    瓈
    0.44
    POSITIVE LOGITS
    in
    0.59
    value
    0.48
    question
    0.47
    a
    0.46
    newer
    0.46
     in
    0.46
    content
    0.46
    likely
    0.46
    conversation
    0.46
    designed
    0.45
    Activations Density 0.000%

    No Known Activations