© 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. 49000
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    öße
    -0.88
    过头
    -0.86
    ordum
    -0.82
     τέ
    -0.79
    DUCT
    -0.79
     fact
    -0.77
     aidé
    -0.75
     sorts
    -0.75
    adering
    -0.75
     berbicara
    -0.74
    POSITIVE LOGITS
     berikut
    0.86
    Arth
    0.85
     folgte
    0.85
    hemm
    0.82
    την
    0.76
     binh
    0.76
     berkualitas
    0.76
     Arth
    0.75
    rotz
    0.75
     твой
    0.75
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.