© 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. 10-GEMMASCOPE-RES-131K
    7. 113409
    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
     already
    -1.37
     too
    -1.36
     уничто
    -1.30
    個人的には
    -1.27
    也在
    -1.27
     большинстве
    -1.25
     extracción
    -1.24
    いただいて
    -1.23
     why
    -1.21
    こちらも
    -1.21
    POSITIVE LOGITS
     they
    1.88
    ками
    1.45
     Consumo
    1.41
     will
    1.37
    THEY
    1.34
     Obtén
    1.32
     jamais
    1.30
    з
    1.29
    ABIL
    1.29
    не
    1.29
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.