Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8289
    Prev
    Next
    INDEX
    Explanations

    data preprocessing or cleaning

    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
    down
    0.50
    to
    0.47
    as
    0.46
    سی
    0.46
    ك
    0.46
    defined
    0.44
    uoso
    0.43
     favoured
    0.42
    lessness
    0.42
     preclude
    0.41
    POSITIVE LOGITS
     rö
    0.54
     이해
    0.51
     송
    0.50
     нико
    0.50
     lähe
    0.49
     ök
    0.49
     tên
    0.48
     gönd
    0.48
     jato
    0.48
     ชื่อ
    0.47
    Activations Density 0.004%

    No Known Activations