© 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. 13717
    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
    菝
    -1.50
     deliciosos
    -1.44
    .”
    -1.41
    ⢊
    -1.37
    ኵ
    -1.36
     of
    -1.35
    </strong>
    -1.33
     весен
    -1.32
    pinephrine
    -1.32
    волю
    -1.32
    POSITIVE LOGITS
    -
    1.45
     Они
    1.38
     debería
    1.27
     that
    1.26
     offiziellen
    1.23
     Since
    1.23
     Because
    1.22
     Если
    1.20
     They
    1.16
     Unlike
    1.15
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.