© 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. 59446
    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
    﨑
    -1.03
    okość
    -1.02
    ladas
    -1.01
    hdysval
    -0.98
     knows
    -0.97
    riks
    -0.94
     lisboa
    -0.93
     cheery
    -0.93
     rũ
    -0.92
    कृति
    -0.91
    POSITIVE LOGITS
     első
    0.90
    {};
    0.90
     чёр
    0.85
    }*/
    0.82
     his
    0.81
    argento
    0.79
    `)
    0.79
    えて
    0.79
     Baca
    0.79
    jala
    0.78
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.