© 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. 75341
    Prev
    Next
    INDEX
    Explanations

    video camera and editing

    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
     vuelto
    -1.26
    熾
    -1.23
    pecabe
    -1.21
     españ
    -1.19
    lový
    -1.19
     on
    -1.18
    خخ
    -1.16
    )]);
    -1.16
     offiziell
    -1.16
     bedeut
    -1.15
    POSITIVE LOGITS
     nimi
    1.31
     verba
    1.29
     televisiva
    1.20
     artisti
    1.15
     require
    1.13
     creativa
    1.13
     nini
    1.12
     opini
    1.12
     fondu
    1.11
    hie
    1.08
    Activations Density 0.055%

    No Known Activations