© 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. 73499
    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
    boné
    -1.16
    ﾕ
    -1.06
    之类的
    -1.06
     kampus
    -1.05
     Ejecutivo
    -1.04
    因为它
    -1.03
     vendeurs
    -1.02
    ESTONE
    -1.02
     เก็
    -1.01
     エントランス
    -0.96
    POSITIVE LOGITS
    ”
    1.07
     he
    1.01
     ”
    1.00
    "
    1.00
    ors
    1.00
    0.99
    7
    0.98
    ...
    0.94
    1
    0.93
     but
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.