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. 52856
    Prev
    Next
    INDEX
    Explanations

    numbered list item introduction

    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
    コの
    0.83
    辣椒
    0.75
    हों
    0.72
    owskiego
    0.71
    circulation
    0.69
    няка
    0.69
     అనేది
    0.68
    늑
    0.68
     STORIES
    0.67
    ceğ
    0.67
    POSITIVE LOGITS
     `
    0.68
    science
    0.67
    `,`
    0.66
    alus
    0.66
    ice
    0.66
    field
    0.64
     descriptive
    0.64
    </
    0.63
     field
    0.63
     stimuli
    0.63
    Activations Density 0.022%

    No Known Activations