© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64876
    Prev
    Next
    INDEX
    Explanations

    Zim, Zem, Zym, Zimb, Zempl

    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
    reté
    -0.74
    creen
    -0.71
     characteristic
    -0.71
     configuration
    -0.71
    Ducks
    -0.69
    approximate
    -0.68
     kvad
    -0.68
     vollständige
    -0.68
    がありません
    -0.68
    ardia
    -0.67
    POSITIVE LOGITS
     kiếm
    0.83
     Zim
    0.82
     Zum
    0.76
     tweezers
    0.76
    ്ട
    0.75
    Integrated
    0.75
     collaborator
    0.74
    zum
    0.74
     Fathers
    0.73
     cip
    0.73
    Activations Density 0.015%

    No Known Activations