© 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. 22-GEMMASCOPE-RES-131K
    7. 14470
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     biela
    -1.63
    ikti
    -1.60
     évé
    -1.60
    szt
    -1.59
     popis
    -1.53
     triko
    -1.53
    鏨
    -1.53
     kenal
    -1.50
     türkiye
    -1.48
     Meksi
    -1.46
    POSITIVE LOGITS
    u
    1.91
    T
    1.78
    U
    1.66
    ar
    1.59
    h
    1.59
    j
    1.56
    F
    1.55
    te
    1.55
    L
    1.53
    E
    1.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.