© 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. 31614
    Prev
    Next
    INDEX
    Explanations

    mixed languages and code snippets

    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
     punto
    -0.86
     bronz
    -0.77
     PCIe
    -0.75
     Luf
    -0.71
    tache
    -0.71
     ESTIM
    -0.70
    Pian
    -0.69
     POINTS
    -0.69
    ள்
    -0.69
     niej
    -0.68
    POSITIVE LOGITS
    赤
    0.75
    円で
    0.74
     Sorgen
    0.74
     vermelha
    0.72
     quá
    0.72
     intensively
    0.67
    hatikan
    0.66
     does
    0.66
     detailed
    0.66
     puertas
    0.66
    Activations Density 0.024%

    No Known Activations