© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102111
    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
     ethnographic
    -1.13
     EFF
    -1.09
    ёв
    -1.04
    ాయ
    -1.03
    Dietary
    -1.00
    UpdateDate
    -0.96
     LEAST
    -0.96
    cepto
    -0.94
     personnalité
    -0.93
    silence
    -0.92
    POSITIVE LOGITS
    hoda
    1.00
    ou
    0.99
     then
    0.92
     сет
    0.92
    up
    0.92
     supporting
    0.91
    烘
    0.86
    羈
    0.85
     сним
    0.85
    剋
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.