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. 29-GEMMASCOPE-2-RES-262K
    4. 583
    Prev
    Next
    INDEX
    Explanations

    HTML title and summary

    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
     ←
    0.70
    ─
    0.67
    [{}\
    0.67
    鋈
    0.66
     Dele
    0.65
    娣
    0.64
    -${
    0.63
    }^{*}
    0.63
     যাই
    0.62
    ^{*}+
    0.62
    POSITIVE LOGITS
     cref
    0.97
    param
    0.83
     param
    0.69
    >/
    0.65
    /∂
    0.64
    ption
    0.59
    ///
    0.59
    returns
    0.58
     фами
    0.58
    >(
    0.58
    Activations Density 0.014%

    No Known Activations