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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7358
    Prev
    Next
    INDEX
    Explanations

    html structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
     כך
    0.60
    [
    0.51
    ar
    0.50
     rans
    0.50
     appunto
    0.49
    ます
    0.48
     wording
    0.47
    perturb
    0.47
    ASTIC
    0.46
    ন
    0.46
    POSITIVE LOGITS
    к
    0.54
    rk
    0.53
    kN
    0.52
    ை
    0.51
     tern
    0.49
    )}+\
    0.49
    is
    0.48
    гийн
    0.47
    shopify
    0.47
    stmt
    0.47
    Activations Density 2.693%

    No Known Activations