© 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. 7633
    Prev
    Next
    INDEX
    Explanations

    directory names and file operations

    np_acts-logits-general · gemini-2.5-flash-lite

    technical and code-oriented tokens—programming identifiers, API/module names, constants, and formal keywords typical of instructional snippets and engineering text

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    وعه
    0.33
    WebApplication
    0.31
     tallow
    0.30
     কমন
    0.30
    aneers
    0.30
     Wesleyan
    0.30
     Masonic
    0.29
     Methyl
    0.29
     coyote
    0.29
     Adoption
    0.29
    POSITIVE LOGITS
     containing
    0.39
    上の
    0.38
    時点で
    0.37
    containing
    0.37
    変換
    0.36
     generate
    0.35
    converting
    0.34
    your
    0.34
     subtraction
    0.33
    𝘀
    0.33
    Activations Density 1.066%

    No Known Activations