© 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. 92930
    Prev
    Next
    INDEX
    Explanations

    barryvdh, barry wilner, barry manilow

    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
     namelijk
    -0.75
    bolsa
    -0.75
    verture
    -0.71
     gør
    -0.71
    }{*}{
    -0.71
     dried
    -0.70
    ૨
    -0.70
    бие
    -0.69
     Азербай
    -0.68
     letech
    -0.66
    POSITIVE LOGITS
     neglecting
    0.93
    diction
    0.78
    uas
    0.77
     פון
    0.77
    бари
    0.71
     Kartu
    0.71
     žá
    0.70
    erro
    0.70
    Premi
    0.69
     druhé
    0.69
    Activations Density 0.075%

    No Known Activations