© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14024
    Prev
    Next
    INDEX
    Explanations

    function return statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    蚬
    0.42
    是通过
    0.40
     गाइड
    0.39
    anía
    0.39
     oto
    0.38
    羰
    0.37
     কণ্ঠে
    0.36
     guía
    0.35
    通过
    0.35
    barn
    0.35
    POSITIVE LOGITS
     .
    0.44
     totalement
    0.43
     fruitless
    0.43
     Secondly
    0.41
    !.
    0.41
    terminate
    0.40
    />
    0.39
     huge
    0.38
     senseless
    0.38
    $.
    0.38
    Activations Density 0.031%

    No Known Activations