© 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. 119496
    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
     still
    -1.27
     this
    -1.25
     or
    -1.20
     these
    -1.17
    While
    -1.13
     Having
    -1.09
     with
    -1.08
    Having
    -1.07
    Ironically
    -1.05
    '
    -1.05
    POSITIVE LOGITS
    ఽ
    1.28
     comentário
    1.14
     ſever
    1.13
     consentimento
    1.13
    ompi
    1.13
     accidente
    1.13
     daca
    1.11
     convite
    1.10
     incidente
    1.10
    zzled
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.