Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100780
    Prev
    Next
    INDEX
    Explanations

    words or phrases denoting relationship or role

    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
    主題
    0.47
    長
    0.46
     аба
    0.45
    }_
    0.45
    陇
    0.44
    ки
    0.44
    Personality
    0.44
    Rüyada
    0.44
    小さ
    0.43
    长
    0.43
    POSITIVE LOGITS
     bilingual
    0.52
     aquatic
    0.46
     elimination
    0.45
     experiment
    0.44
     mathematical
    0.44
     new
    0.43
     lego
    0.43
     korean
    0.42
     bilinear
    0.42
     schools
    0.42
    Activations Density 0.004%

    No Known Activations