© 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. 79427
    Prev
    Next
    INDEX
    Explanations

    new concept

    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
    cún
    -1.11
    
    -1.03
    ový
    -1.02
    ⏮
    -1.01
    ulity
    -1.01
    wych
    -0.99
    eclamp
    -0.99
    lotte
    -0.99
    𝟖
    -0.99
     heut
    -0.96
    POSITIVE LOGITS
     new
    10.75
    new
    7.00
    新的
    6.28
     neuen
    6.16
     nuevos
    5.56
     nuevas
    5.56
     جدید
    5.47
     nieuwe
    5.47
     új
    5.41
     nuovi
    5.38
    Activations Density 1.079%

    No Known Activations