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. 7257
    Prev
    Next
    INDEX
    Explanations

    key phrase

    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
    нд
    0.80
    ustainability
    0.75
     आसपास
    0.71
     但是
    0.70
    遉
    0.70
    cellaneous
    0.69
    Zobacz
    0.68
     vendu
    0.68
     potuto
    0.67
    اری
    0.67
    POSITIVE LOGITS
    ed
    0.91
    e
    0.84
    en
    0.78
    o
    0.75
    a
    0.75
    i
    0.74
    お
    0.74
    er
    0.73
    r
    0.69
     Emeritus
    0.69
    Activations Density 0.415%

    No Known Activations