© 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. 120391
    Prev
    Next
    INDEX
    Explanations

    math notation and structure

    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
    ти
    0.77
    の
    0.72
     کرد
    0.71
     for
    0.69
     and
    0.68
    Mode
    0.67
    ستی
    0.67
    ター
    0.66
    দের
    0.66
    의
    0.65
    POSITIVE LOGITS
     assertions
    0.76
    ien
    0.74
    !
    0.73
    t
    0.73
    o
    0.72
     eredmény
    0.71
    га
    0.70
    ，
    0.68
    ik
    0.67
    รับ
    0.67
    Activations Density 0.000%

    No Known Activations