© 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. 26715
    Prev
    Next
    INDEX
    Explanations

    quantities and counting

    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
    ه
    0.67
    a
    0.59
    ה
    0.58
    Я
    0.53
    Mutation
    0.52
    া
    0.48
    answers
    0.46
    кто
    0.46
    Answers
    0.45
    贤
    0.44
    POSITIVE LOGITS
     ս
    0.46
     in
    0.46
    əri
    0.46
    əsi
    0.46
     anthropological
    0.45
    weixin
    0.44
    天氣
    0.44
    adă
    0.44
     forbindelse
    0.44
    டெ
    0.44
    Activations Density 0.000%

    No Known Activations