© 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. 10-GEMMASCOPE-RES-131K
    7. 129700
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </strong>
    -1.42
     was
    -1.41
     anything
    -1.31
    并且
    -1.30
    </h2>
    -1.29
     edizione
    -1.16
     esas
    -1.12
     even
    -1.12
     something
    -1.11
    ↵
    -1.10
    POSITIVE LOGITS
     unangemess
    1.36
     Eigentü
    1.34
     städ
    1.32
     falschen
    1.31
     plupart
    1.30
     grossen
    1.28
     撮っ
    1.27
     gän
    1.27
     Với
    1.26
     kreeg
    1.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.