© 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. 44232
    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
    🍣
    -0.98
     stratég
    -0.94
     Generale
    -0.90
     Reproductive
    -0.85
     SCHED
    -0.85
     COLLE
    -0.83
    ง่าย
    -0.82
    Hydra
    -0.82
    콧
    -0.82
     publié
    -0.81
    POSITIVE LOGITS
    also
    1.05
    they
    0.95
    with
    0.94
     maneiras
    0.93
    due
    0.91
     bancaria
    0.90
     САД
    0.90
     obyvateľov
    0.90
     Téléchargez
    0.89
    ťa
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.