© 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. 22-GEMMASCOPE-RES-131K
    7. 32907
    Prev
    Next
    INDEX
    Explanations

    total numbers and quantities

    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_22/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
     Sør
    -0.82
    orsz
    -0.81
    jMenuItem
    -0.81
     it
    -0.77
     absur
    -0.74
    ValidationError
    -0.74
     unga
    -0.73
     Kitz
    -0.73
    分数
    -0.73
    議員
    -0.73
    POSITIVE LOGITS
     insgesamt
    1.40
     total
    1.24
     Insgesamt
    1.13
     totaling
    1.09
     collectively
    1.03
     overall
    1.03
     कुल
    1.01
    ทั้งหมด
    0.97
     összes
    0.96
    overall
    0.96
    Activations Density 0.092%

    No Known Activations