© 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. 93783
    Prev
    Next
    INDEX
    Explanations

    interrogative sentence or list

    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
     brind
    0.45
     לק
    0.45
    eq
    0.43
     jit
    0.41
    Hin
    0.41
     +
    0.40
     શ
    0.40
    マン
    0.40
    ྡ
    0.40
     ແລະ
    0.40
    POSITIVE LOGITS
    對方
    0.48
     ظاهر
    0.46
     الجمهور
    0.45
     pobreza
    0.45
    الية
    0.44
    птова
    0.44
     внешний
    0.44
    ы
    0.44
    تاح
    0.43
    زاء
    0.43
    Activations Density 0.000%

    No Known Activations