© 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. 22-GEMMASCOPE-RES-131K
    7. 72673
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     sabes
    -1.03
     начин
    -0.96
     sabía
    -0.95
    してた
    -0.94
    niña
    -0.94
     peinados
    -0.92
     erbjud
    -0.91
     razas
    -0.89
     aprendido
    -0.89
     tráiler
    -0.89
    POSITIVE LOGITS
     also
    1.01
    /*++
    0.99
    IModel
    0.98
    ourced
    0.97
    reibt
    0.97
    ))]
    0.94
     fanta
    0.93
    >.
    0.92
    TION
    0.91
     formy
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.