© 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. 105060
    Prev
    Next
    INDEX
    Explanations

    continues with

    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
    
    -2.00
     Fällen
    -1.77
     récomp
    -1.66
    찮
    -1.66
     случаях
    -1.59
     desactivar
    -1.59
     Umständen
    -1.58
     Если
    -1.58
    ਃ
    -1.58
     réjou
    -1.55
    POSITIVE LOGITS
     are
    2.00
     in
    1.83
    のような
    1.70
     a
    1.65
     unable
    1.59
     without
    1.56
     like
    1.54
    の内
    1.50
    ury
    1.46
    纮
    1.45
    Activations Density 0.008%

    No Known Activations