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. 29-GEMMASCOPE-2-RES-262K
    4. 790
    Prev
    Next
    INDEX
    Explanations

    numbers 0.0

    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
    භ
    0.73
    atz
    0.71
    ರ್‌
    0.70
     quasi
    0.69
    quasi
    0.69
     cosplay
    0.69
    Nepali
    0.68
     handlerInput
    0.67
    iste
    0.66
    usian
    0.66
    POSITIVE LOGITS
    0
    0.87
    ০০০
    0.82
    ০০
    0.78
    URNING
    0.75
    ၀၀
    0.71
    0
    0.69
    ០០
    0.69
    ૦
    0.65
    ۰۰
    0.64
    ००
    0.63
    Activations Density 0.150%

    No Known Activations