© 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-65K
    7. 349
    Prev
    Next
    INDEX
    Explanations

    Upwork, upper level

    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_65k_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
    ח
    1.05
    ى
    0.90
    ین
    0.86
    ز
    0.86
    ט
    0.86
    א
    0.85
    л
    0.79
    ק
    0.75
    ב
    0.74
    ע
    0.74
    POSITIVE LOGITS
    -
    0.72
     (
    0.67
    nement
    0.64
    abilir
    0.62
    ning
    0.61
    '
    0.61
    lighting
    0.60
    գ
    0.60
    ness
    0.60
    ként
    0.59
    Activations Density 0.912%

    No Known Activations