© 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. 33345
    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
     promesse
    -1.30
    猻
    -1.27
    鷽
    -1.27
     получите
    -1.26
     土産
    -1.26
     Sénégal
    -1.23
    Daha
    -1.22
     APPELL
    -1.22
    İş
    -1.22
     satisfactor
    -1.21
    POSITIVE LOGITS
     And
    1.38
    了一些
    1.23
     untuk
    1.21
    さんに
    1.20
     Don
    1.16
    However
    1.16
    場所で
    1.16
     '
    1.16
    々に
    1.15
    数百
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.