© 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. 16-GEMMASCOPE-2-RES-262K
    7. 109940
    Prev
    Next
    INDEX
    Explanations

    domain availability and manifesto

    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_16_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
     kiire
    0.50
     kuulu
    0.49
    ர்களும்
    0.48
    är
    0.47
     č
    0.46
    č
    0.46
     usted
    0.46
    大哥
    0.46
     kemudian
    0.45
     झा
    0.45
    POSITIVE LOGITS
    사
    0.56
    for
    0.53
    ريس
    0.53
     separators
    0.52
    的想法
    0.52
    ধন
    0.52
    مو
    0.51
    shifted
    0.51
    啭
    0.51
    לי
    0.50
    Activations Density 0.000%

    No Known Activations