© 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. 25108
    Prev
    Next
    INDEX
    Explanations

    left/right nodes

    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
    Negative Logits
    已经
    -0.98
    already
    -0.98
     miliar
    -0.97
    intend
    -0.97
     detayl
    -0.96
     vetores
    -0.93
    っていた
    -0.93
     préstamo
    -0.91
     hazır
    -0.90
     komplette
    -0.90
    POSITIVE LOGITS
    IGNS
    1.13
    멕
    1.07
    nativeElement
    1.06
     después
    0.96
     outlet
    0.93
    malink
    0.91
     branches
    0.91
     was
    0.91
    ஂ
    0.88
    ISTO
    0.86
    Activations Density 0.002%

    No Known Activations