© 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. 3165
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

    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
     legs
    0.65
    腿
    0.60
     twice
    0.60
     suppression
    0.59
     reflected
    0.59
     suppressed
    0.57
    İ
    0.56
     purpos
    0.56
    ↵
    0.56
     legislation
    0.56
    POSITIVE LOGITS
    𝘀
    1.14
    𝘇
    1.07
    𝐬
    1.05
    /");
    1.04
    𝘴
    1.04
    /")
    1.03
    ٰذا
    0.98
    /";
    0.98
     ___
    0.98
    𝚝
    0.96
    Activations Density 0.543%

    No Known Activations