© 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. 106394
    Prev
    Next
    INDEX
    Explanations

    log tag

    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
    Negative Logits
     here
    -1.14
     aquí
    -0.99
     здесь
    -0.93
    duğu
    -0.80
     ElementRef
    -0.79
    Răspunde
    -0.78
    EObject
    -0.77
    爵
    -0.77
    [])
    -0.77
    ฟัง
    -0.76
    POSITIVE LOGITS
     TAG
    3.11
    TAG
    2.70
     tag
    2.16
    tag
    1.96
     Tag
    1.85
    Tag
    1.78
     tags
    1.68
     tagged
    1.57
     tagging
    1.44
    调试
    1.37
    Activations Density 0.010%

    No Known Activations