© 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. 106308
    Prev
    Next
    INDEX
    Explanations

    Q, Suite, Kurt, The, This, invention, traits, serial

    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
    щины
    -0.78
     årene
    -0.76
     nvidia
    -0.73
    zów
    -0.73
    PSU
    -0.72
    ONTO
    -0.72
    ampton
    -0.72
     JSONException
    -0.71
     اتحاد
    -0.71
     ndani
    -0.71
    POSITIVE LOGITS
     لع
    0.86
     struct
    0.81
    ímos
    0.80
     Win
    0.75
     necesitar
    0.75
     yếu
    0.73
    Carex
    0.73
     login
    0.72
    losses
    0.72
    AYSIA
    0.71
    Activations Density 0.000%

    No Known Activations