© 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. 47594
    Prev
    Next
    INDEX
    Explanations

    putative, callable

    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
     și
    -2.89
    および
    -2.67
     और
    -2.55
     garganta
    -2.52
     zijn
    -2.48
    蔔
    -2.34
    ifikant
    -2.31
    芣
    -2.28
     maquillage
    -2.27
     ciment
    -2.27
    POSITIVE LOGITS
     Of
    3.36
    );
    3.22
     erwähnten
    2.86
     bekannten
    2.72
    0
    2.66
     claramente
    2.50
     másik
    2.39
     But
    2.38
    은
    2.34
     Ausblick
    2.31
    Activations Density 0.013%

    No Known Activations