© 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. 3626
    Prev
    Next
    INDEX
    Explanations

    Roman de, François Lar

    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
     (
    -1.09
     Med
    -0.85
     just
    -0.83
    UnityEngine
    -0.82
     الوجه
    -0.79
     continuación
    -0.78
    /}{
    -0.78
     do
    -0.77
    デル
    -0.77
     Goldsmith
    -0.75
    POSITIVE LOGITS
     mencionó
    0.97
     mangiare
    0.92
     abbraccio
    0.91
    válasz
    0.88
    除非
    0.88
     만화
    0.85
    caracter
    0.84
     sosis
    0.84
     einzige
    0.83
    Minden
    0.83
    Activations Density 0.000%

    No Known Activations