© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107936
    Prev
    Next
    INDEX
    Explanations

    French names and figures

    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
    Not in Any Lists

    No Comments

    Negative Logits
     perles
    -0.91
    arté
    -0.90
     burglar
    -0.90
     oeufs
    -0.90
    ishe
    -0.88
    ulents
    -0.86
    ėj
    -0.85
     vache
    -0.81
     sentiers
    -0.79
    mètres
    -0.79
    POSITIVE LOGITS
     Jansen
    0.89
     Buff
    0.85
    utilité
    0.84
    OURCE
    0.83
    czaj
    0.81
    的爱
    0.81
    plt
    0.79
    о
    0.79
    ΜΑ
    0.79
    farin
    0.79
    Activations Density 0.050%

    No Known Activations