© 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. 109827
    Prev
    Next
    INDEX
    Explanations

    celebrating events and milestones

    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
     و
    0.71
     ו
    0.70
    ים
    0.63
    姥
    0.54
     удосто
    0.54
    ों
    0.53
     dichas
    0.53
     mantenerse
    0.53
     د
    0.52
     لأ
    0.52
    POSITIVE LOGITS
    oje
    0.81
    eşit
    0.70
    et
    0.69
    是不是
    0.68
    alid
    0.66
    o
    0.66
    as
    0.66
    yce
    0.66
    การ
    0.65
     الايه
    0.65
    Activations Density 0.001%

    No Known Activations