© 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. 64907
    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
    昀
    -1.14
    幛
    -1.13
    )।
    -1.13
     compréhen
    -1.06
     asfal
    -1.06
    huur
    -1.05
    떳
    -1.05
     kompati
    -1.05
     tanggal
    -1.05
    革命
    -1.05
    POSITIVE LOGITS
     possi
    1.21
     einiger
    1.17
     possib
    1.15
    战术
    1.15
    があり
    1.13
     mehrerer
    1.11
     einzel
    1.11
    けど
    1.10
    几个人
    1.09
     Sortiment
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.