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. 1953
    Prev
    Next
    INDEX
    Explanations

    compound annual growth rate

    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
     elementary
    0.51
     art
    0.42
     d
    0.41
     non
    0.41
     '
    0.41
     resolve
    0.40
     un
    0.39
     animals
    0.39
     une
    0.39
     Integer
    0.38
    POSITIVE LOGITS
     confertim
    0.71
    padă
    0.71
    निवेश
    0.71
    📨
    0.70
     könne
    0.68
    CTime
    0.68
    漃
    0.68
    صیٰ
    0.67
     Букмекердик
    0.67
     Бушлай
    0.66
    Activations Density 0.001%

    No Known Activations