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. 14839
    Prev
    Next
    INDEX
    Explanations

    dries independently

    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
    Fullscreen
    0.49
    ñado
    0.47
    Klik
    0.46
    Ketika
    0.45
    𝚗
    0.45
    Você
    0.45
    करे
    0.44
    Muito
    0.44
    你的
    0.44
    пления
    0.44
    POSITIVE LOGITS
     (
    0.54
     [
    0.47
     at
    0.46
     ar
    0.45
    (
    0.43
     Assembly
    0.43
     hang
    0.42
     SS
    0.40
    ,,
    0.40
     Cycling
    0.40
    Activations Density 0.005%

    No Known Activations