© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144186
    Prev
    Next
    INDEX
    Explanations

    comma-delimited lists or producing

    np_acts-logits-general · gemini-2.5-flash-lite

    severity level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     IL
    0.49
     shabby
    0.49
     MAR
    0.48
     tuoi
    0.46
     mango
    0.46
     bloody
    0.45
     bric
    0.45
    çok
    0.45
     arctic
    0.45
     l
    0.45
    POSITIVE LOGITS
    افة
    0.50
    规则
    0.49
    配置文件
    0.49
     Gegenwart
    0.48
    歼
    0.48
    StopTime
    0.48
    нії
    0.46
    ScriptName
    0.46
     exploits
    0.46
    对话
    0.46
    Activations Density 0.000%

    No Known Activations