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. 17-GEMMASCOPE-2-RES-65K
    4. 47126
    Prev
    Next
    INDEX
    Explanations

    reply now

    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_17_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
    Couldn
    1.38
     आवेदक
    1.21
    l
    1.18
    STOP
    1.14
    Comparable
    1.14
    مول
    1.14
    lere
    1.13
    間に
    1.11
    胛
    1.10
    Suppose
    1.09
    POSITIVE LOGITS
    ionicons
    1.48
    itäts
    1.42
    ри
    1.42
     불구하고
    1.41
    р
    1.38
    ٹ
    1.34
    사용
    1.33
     fech
    1.30
    waża
    1.22
     Setiap
    1.20
    Activations Density 0.000%

    No Known Activations