© 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. 40-GEMMASCOPE-2-RES-262K
    7. 110902
    Prev
    Next
    INDEX
    Explanations

    age and gender of people

    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_40_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
     değiştir
    0.40
    پيديا
    0.39
    ২
    0.39
    ปี
    0.39
     ²
    0.39
    迵
    0.38
    빱
    0.38
    ²/
    0.38
     pathophysiology
    0.38
     Định
    0.37
    POSITIVE LOGITS
    ючись
    0.46
     middle
    0.44
     present
    0.39
     серед
    0.39
     maximum
    0.38
     выйти
    0.38
     Steel
    0.36
     geworden
    0.36
     mid
    0.36
    uple
    0.35
    Activations Density 0.003%

    No Known Activations