© 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. 111485
    Prev
    Next
    INDEX
    Explanations

    basic completion and continuation

    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
    0.52
    (
    0.52
    s
    0.46
     Sie
    0.46
    া
    0.45
    Look
    0.45
    otta
    0.45
    ше
    0.44
     Respons
    0.44
    ા
    0.44
    POSITIVE LOGITS
     ಮೇಲೆ
    0.49
     mischiev
    0.48
     quantized
    0.47
    を踏
    0.47
     texId
    0.46
     civilized
    0.46
     ostrich
    0.46
     sweaters
    0.45
     entice
    0.45
     식
    0.45
    Activations Density 0.002%

    No Known Activations