© 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. 34-GEMMASCOPE-RES-131K
    7. 31696
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    posizioni
    -0.82
     Και
    -0.79
    Listing
    -0.78
    ůž
    -0.77
     zaragoza
    -0.74
    𝒉
    -0.73
     veiks
    -0.73
     đó
    -0.72
     australiano
    -0.72
    reathe
    -0.72
    POSITIVE LOGITS
    っており
    0.83
    舘
    0.82
     [];
    0.79
     oven
    0.79
     templates
    0.78
    şa
    0.78
    वास
    0.77
     theta
    0.77
     ".";
    0.77
    amir
    0.75
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.