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-65K
    4. 1470
    Prev
    Next
    INDEX
    Explanations

    list items

    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_65k_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
     $*$-
    0.96
     $*$
    0.90
     $*
    0.86
    
    0.86
     .*
    0.81
    ^{*}+
    0.79
     *\
    0.75
    ^{*}$-
    0.75
     *)
    0.75
    ^*\
    0.74
    POSITIVE LOGITS
    Brazil
    0.85
    Due
    0.80
    Another
    0.78
    Siempre
    0.78
    British
    0.77
    These
    0.76
    udy
    0.76
    Paid
    0.75
    Links
    0.75
    Throughout
    0.75
    Activations Density 0.740%

    No Known Activations