© 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. 22-GEMMASCOPE-RES-131K
    7. 12447
    Prev
    Next
    INDEX
    Explanations

    dates and volumes

    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
     which
    -1.00
     defendant
    -0.99
     და
    -0.98
    Referințe
    -0.94
    прият
    -0.94
     листья
    -0.93
     Ка
    -0.92
    сль
    -0.92
    顔が
    -0.92
     Akte
    -0.92
    POSITIVE LOGITS
     memasukkan
    1.02
    Opin
    0.96
    INDICE
    0.94
     آتش
    0.94
     preços
    0.94
     Demolition
    0.93
     قوان
    0.93
    Interes
    0.92
    constexpr
    0.92
    Dile
    0.90
    Activations Density 0.008%

    No Known Activations