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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7555
    Prev
    Next
    INDEX
    Explanations

    snakes, serpents, pythons

    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
    ל
    2.78
    ğer
    2.64
    SQLALCHEMY
    2.58
    𝓊
    2.52
    a
    2.47
    𝑠
    2.44
     lectura
    2.40
     behalf
    2.31
    自觉
    2.30
    ண்க
    2.30
    POSITIVE LOGITS
    и
    3.58
    ی
    3.46
    ي
    3.15
    मताओं
    3.06
    ে
    3.01
    i
    3.01
     zespołu
    3.01
    থেষ্ট
    2.94
     rumored
    2.89
    けど
    2.84
    Activations Density 0.138%

    No Known Activations