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. 22-GEMMASCOPE-2-RES-65K
    4. 3419
    Prev
    Next
    INDEX
    Explanations

    sequences and explanations

    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_22_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
    ess
    0.85
    е
    0.78
    ¯</
    0.76
    iff
    0.72
    다라고
    0.72
    </strong>
    0.68
     di
    0.63
    ade
    0.61
     bu
    0.61
    ⅽ
    0.60
    POSITIVE LOGITS
    There
    1.38
    These
    1.28
    Beyond
    1.27
    Following
    1.26
    Here
    1.23
    Several
    1.23
    Below
    1.22
    以下の
    1.20
    Despite
    1.20
    Combin
    1.19
    Activations Density 0.381%

    No Known Activations