© 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. 113121
    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
     will
    -0.98
     your
    -0.94
     should
    -0.93
    𝟐
    -0.90
    found
    -0.90
    謁
    -0.89
    ०
    -0.89
     no
    -0.88
     devi
    -0.88
     deviate
    -0.88
    POSITIVE LOGITS
     พื้น
    1.07
    遵守
    1.05
     Dz
    1.00
    一直在
    0.99
    っぷり
    0.99
    zyka
    0.98
     Sunlight
    0.97
     zarówno
    0.97
    zação
    0.97
     Где
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.