© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130900
    Prev
    Next
    INDEX
    Explanations

    key concepts before "of" or "the"

    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_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
    .
    -1.59
     ця
    -1.34
     is
    -1.30
     The
    -1.28
    ことなく
    -1.23
     sophie
    -1.23
     qed
    -1.20
    sellor
    -1.20
    かを
    -1.20
    なりに
    -1.19
    POSITIVE LOGITS
     blusas
    1.78
     fundación
    1.69
    diferentes
    1.61
     almofada
    1.53
     sudadera
    1.50
     pulseira
    1.49
     housse
    1.45
     juguetes
    1.45
     faldas
    1.43
    DAFTAR
    1.42
    Activations Density 0.052%

    No Known Activations