© 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. 22-GEMMASCOPE-RES-131K
    7. 65535
    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
     flotte
    -1.23
    trusive
    -1.09
     ۱۳۸
    -1.05
    Ито
    -1.05
    реб
    -1.03
     avvic
    -1.03
    Karakteristik
    -1.03
     πρ
    -1.02
     État
    -1.02
     konsep
    -1.02
    POSITIVE LOGITS
    ционное
    1.16
    ционная
    1.08
     gezond
    1.04
     frenos
    1.02
     wohin
    1.02
     frecuentemente
    1.02
     ciertamente
    1.00
    .!
    0.98
     composición
    0.97
     BSEB
    0.97
    Activations Density 0.018%

    No Known Activations