© 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. 31-GEMMASCOPE-2-RES-262K
    7. 1442
    Prev
    Next
    INDEX
    Explanations

    news and aesthetic qualities

    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_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
    军事
    0.33
    áty
    0.30
    
    0.30
    🤨
    0.29
     скры
    0.29
     кризи
    0.29
     সামরিক
    0.29
    ্‌
    0.29
    Logistic
    0.29
    íncipe
    0.28
    POSITIVE LOGITS
     civilian
    0.50
     civilians
    0.43
     softer
    0.33
     superficial
    0.33
     aesthetic
    0.32
     merr
    0.31
     shallower
    0.30
     sweet
    0.30
    GUI
    0.30
     manis
    0.30
    Activations Density 0.922%

    No Known Activations