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. 29-GEMMASCOPE-2-RES-262K
    4. 52804
    Prev
    Next
    INDEX
    Explanations

    GTPase, damp towel, float input

    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_29_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
    handlebars
    0.71
    Ing
    0.71
     વ
    0.71
    VCT
    0.65
     ટ
    0.63
    Package
    0.62
     แท
    0.61
     ing
    0.60
    ्
    0.60
    ٘
    0.60
    POSITIVE LOGITS
    มูล
    0.67
    মাতে
    0.67
    lucent
    0.66
     red
    0.65
    レッド
    0.63
     rojo
    0.62
     Lem
    0.62
    දි
    0.61
    मूलन
    0.60
     Claus
    0.60
    Activations Density 0.013%

    No Known Activations