© 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. 435
    Prev
    Next
    INDEX
    Explanations

    language or code identifiers

    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
    ل
    0.66
    ون
    0.60
    نا
    0.59
    and
    0.58
    ها
    0.56
    一層
    0.52
    ور
    0.51
    最適
    0.50
    f
    0.49
    л
    0.48
    POSITIVE LOGITS
     to
    0.61
     від
    0.52
     từ
    0.47
     مدينة
    0.45
     políticos
    0.42
     ט
    0.42
    !");
    0.42
     académicos
    0.42
    !”,
    0.41
     الك
    0.41
    Activations Density 2.172%

    No Known Activations