© 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. 73427
    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
    gamon
    -1.09
    }
    -0.97
    cnia
    -0.93
    дис
    -0.92
     nascimento
    -0.92
     Kontexten
    -0.91
     Flowering
    -0.91
    ntable
    -0.91
    ++){
    -0.91
    瑆
    -0.90
    POSITIVE LOGITS
    ras
    0.99
     With
    0.92
    engar
    0.86
    ]
    0.84
    
    0.82
    ALLENG
    0.82
    傭
    0.81
     знать
    0.81
    pop
    0.81
    us
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.