© 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. 7557
    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
    わりに
    -1.09
    готовления
    -1.06
     متحده
    -1.02
    ()?
    -1.01
    észetes
    -0.98
    »։
    -0.98
    UTUP
    -0.95
     frattempo
    -0.94
     tempio
    -0.93
     činnosti
    -0.93
    POSITIVE LOGITS
     gravedad
    0.97
    _
    0.95
    They
    0.92
    想到
    0.90
     fáciles
    0.90
    双眼
    0.89
     milyen
    0.89
     Moz
    0.88
    遇到
    0.88
     .
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.