© 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. 22-GEMMASCOPE-RES-131K
    7. 26840
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Веду
    -1.18
     banheiro
    -1.15
     mediante
    -1.14
     manter
    -1.13
    ≲
    -1.11
     λά
    -1.06
    鸶
    -1.06
    fund
    -1.06
    存于
    -1.05
    iciais
    -1.05
    POSITIVE LOGITS
    rabbitmq
    1.15
    langkah
    1.06
    gestellten
    1.04
     obeying
    0.98
    :
    0.95
    towej
    0.93
    ).
    0.91
     (
    0.89
    After
    0.86
    ЛЬ
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.