© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1418
    Prev
    Next
    INDEX
    Explanations

    all encompassing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
     охла
    1.24
    en
    1.14
    ology
    1.13
     Only
    1.13
    G
    1.09
    ek
    1.07
    Pro
    1.06
     പോലും
    1.04
    B
    1.03
    P
    1.01
    POSITIVE LOGITS
    lllll
    1.76
     demás
    1.67
    llllll
    1.62
    llllllll
    1.58
    uding
    1.57
    itriangular
    1.57
    aitement
    1.50
    iteration
    1.43
     conceivable
    1.41
    <unused828>
    1.40
    Activations Density 0.274%

    No Known Activations