© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65022
    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
     portugués
    -1.29
     might
    -1.24
    OWA
    -1.22
    cupa
    -1.22
     numerous
    -1.21
     adalah
    -1.20
     był
    -1.20
     had
    -1.20
    נוּ
    -1.16
     ucran
    -1.15
    POSITIVE LOGITS
     archaic
    1.39
     masterful
    1.24
    摳
    1.22
    摟
    1.20
     haremos
    1.18
     flashy
    1.15
    ACK
    1.15
     unn
    1.15
     horrid
    1.13
     quintessential
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.