© 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-262K
    7. 31392
    Prev
    Next
    INDEX
    Explanations

    project version SNAPSHOT

    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_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
    聑
    0.67
    䐂
    0.56
    тивных
    0.53
    筫
    0.52
    usega
    0.51
     eğer
    0.51
    ))}{
    0.51
     লীগ
    0.50
    ถ้า
    0.50
    徝
    0.50
    POSITIVE LOGITS
     híbr
    0.59
    Cuánt
    0.57
     hybrid
    0.57
    ר
    0.57
     convirtió
    0.55
    Hybrid
    0.54
    hybrid
    0.53
    evaluation
    0.53
     তীব্র
    0.52
    assessment
    0.52
    Activations Density 0.002%

    No Known Activations