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. 16-GEMMASCOPE-2-RES-262K
    4. 7435
    Prev
    Next
    INDEX
    Explanations

    x and y coordinates

    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_16_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
    ל
    0.52
    plug
    0.50
    st
    0.49
    ئی
    0.48
    کت
    0.48
    in
    0.48
    싶
    0.48
    یت
    0.46
    ihad
    0.45
    Жи
    0.45
    POSITIVE LOGITS
     v
    0.58
     y
    0.56
     koordin
    0.51
     seiner
    0.49
     sulla
    0.48
     его
    0.47
     fecha
    0.47
     REV
    0.47
     menuMobile
    0.47
     Teller
    0.46
    Activations Density 0.711%

    No Known Activations