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. 52876
    Prev
    Next
    INDEX
    Explanations

    code syntax pattern

    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
     ->
    1.48
    )->
    1.38
     --->
    1.25
     =>
    1.24
     ==>
    1.15
     <-
    1.14
     →
    1.14
     -->
    1.14
     ----->
    1.13
    ---->
    1.09
    POSITIVE LOGITS
    setlength
    0.75
    斉
    0.64
     केयर
    0.62
    कालीन
    0.60
     प्रेरित
    0.60
    뿍
    0.59
    ca
    0.59
     గవర్
    0.59
    中文
    0.58
    WindowTitle
    0.58
    Activations Density 0.003%

    No Known Activations