© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 56373
    Prev
    Next
    INDEX
    Explanations

    learning and education

    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_31_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
    !!!
    0.50
     competitors
    0.47
     sellers
    0.46
    !!!!
    0.46
     premiums
    0.44
     foragers
    0.44
     retailers
    0.43
    🧈
    0.43
    くない
    0.43
     abusers
    0.43
    POSITIVE LOGITS
     शिक्षा
    0.53
    Education
    0.52
    Learning
    0.49
     plán
    0.48
    교육
    0.46
     Strengthen
    0.46
     постепенно
    0.46
     эффективно
    0.45
     Strengthening
    0.44
     поня
    0.44
    Activations Density 0.011%

    No Known Activations