© 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. 127642
    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
    ども
    -0.92
    ━━━━
    -0.89
    èvent
    -0.85
    seudo
    -0.85
    Zo
    -0.82
    cise
    -0.81
    Cre
    -0.81
     warship
    -0.81
     libéral
    -0.80
    hah
    -0.79
    POSITIVE LOGITS
     estrena
    1.09
    畦
    1.04
     schneiden
    1.02
    cuba
    0.99
    colas
    0.98
    lipas
    0.97
     drei
    0.96
    tième
    0.96
    wallpapers
    0.95
    jasa
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.