© 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. 25068
    Prev
    Next
    INDEX
    Explanations

    Safari settings

    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
     horloge
    -1.54
     célè
    -1.47
     serre
    -1.45
     cuchar
    -1.45
     choisis
    -1.41
     pensées
    -1.38
     neumáticos
    -1.37
     murale
    -1.37
     brune
    -1.37
     peluche
    -1.36
    POSITIVE LOGITS
    with
    1.27
     there
    1.23
     Even
    1.13
    R
    1.09
     Both
    1.09
    W
    1.05
    F
    1.05
    From
    1.05
    u
    1.04
    L
    1.03
    Activations Density 0.042%

    No Known Activations