© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35406
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     of
    -1.39
     yakni
    -1.05
    ..."
    -1.05
     "...
    -1.02
    ...
    -1.01
     "[
    -0.99
    ędziesz
    -0.97
     "(
    -0.94
    вся
    -0.94
     ugy
    -0.93
    POSITIVE LOGITS
    Добавлено
    1.14
    Отзыв
    1.13
     вагі
    1.07
     enfance
    1.06
     débat
    1.05
     refroid
    1.05
    Tamaño
    1.05
    狁
    1.04
     mentales
    1.04
     démarrage
    1.02
    Activations Density 0.003%

    No Known Activations