Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 36651
    Prev
    Next
    INDEX
    Explanations

    coding variable declarations

    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
    这是一
    0.37
     உள்ளிட்ட
    0.35
     двумя
    0.34
    5
    0.33
    $
    0.32
    ":
    0.31
    $<
    0.31
    +}$,
    0.31
    íl
    0.31
     类
    0.31
    POSITIVE LOGITS
     otro
    0.45
    襪
    0.43
    矯正
    0.42
     coseno
    0.42
    ꫝ
    0.42
     sesuatu
    0.41
    راض
    0.41
     annat
    0.40
     Vaill
    0.40
     एडमिशन
    0.40
    Activations Density 0.111%

    No Known Activations