© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47408
    Prev
    Next
    INDEX
    Explanations

    zero-crossing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    小时
    -0.79
    瘩
    -0.76
    ysław
    -0.75
    
    -0.75
    x
    -0.73
     अच्छ
    -0.73
    heimer
    -0.72
    お菓子
    -0.71
    這種
    -0.70
    标准
    -0.69
    POSITIVE LOGITS
     valued
    0.98
     padding
    0.89
    щение
    0.86
     crossings
    0.85
     duración
    0.85
     crossing
    0.84
    valued
    0.84
    kein
    0.83
     padded
    0.83
    padding
    0.83
    Activations Density 0.026%

    No Known Activations