© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85229
    Prev
    Next
    INDEX
    Explanations

    JBZoo, elle, DBeaver, AgileObjects, Sheng, centrum

    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
     our
    -1.42
     городов
    -1.34
     will
    -1.31
     these
    -1.30
     tricky
    -1.24
     and
    -1.22
     –
    -1.21
    鴣
    -1.21
    顛
    -1.21
    ;
    -1.20
    POSITIVE LOGITS
    romeda
    1.35
    mainly
    1.34
     bè
    1.32
    meist
    1.32
    достатки
    1.28
    ان
    1.28
    mostly
    1.27
    ³.
    1.27
    gezogen
    1.27
     باسلام
    1.26
    Activations Density 0.079%

    No Known Activations