© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1287
    Prev
    Next
    INDEX
    Explanations

    just plain emphasis

    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_16k_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
    ть
    1.78
    λα
    1.71
    Ка
    1.68
    sels
    1.60
    ম্ম
    1.59
     ра
    1.57
    recyclerView
    1.57
    ر
    1.56
     مو
    1.52
    lenen
    1.51
    POSITIVE LOGITS
    ifiably
    4.18
    ifiable
    2.42
    ified
    2.37
     plain
    2.30
     FYI
    2.19
    cbd
    2.14
     downright
    2.12
    单纯
    2.07
     plainly
    1.96
    ification
    1.94
    Activations Density 0.223%

    No Known Activations