Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7431
    Prev
    Next
    INDEX
    Explanations

    what something does:

    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
    кер
    0.84
    fection
    0.84
     alınan
    0.81
    نا
    0.79
     Agama
    0.78
    liners
    0.78
     Selasa
    0.77
    y
    0.77
    اں
    0.77
    oretically
    0.77
    POSITIVE LOGITS
     integrals
    0.96
    :
    0.96
    :
    0.92
    が
    0.91
     στον
    0.87
    ।
    0.84
     intramolecular
    0.84
    。
    0.84
     digestibility
    0.81
     characterizes
    0.81
    Activations Density 0.758%

    No Known Activations