© 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. 104569
    Prev
    Next
    INDEX
    Explanations

    date and time separators

    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
    というわけで
    -1.84
     uska
    -1.66
     "",
    -1.66
     ;
    -1.63
     FEBR
    -1.59
     песню
    -1.56
     harta
    -1.54
    ♩
    -1.54
     peluche
    -1.52
     Chambres
    -1.52
    POSITIVE LOGITS
     or
    1.79
     it
    1.76
     and
    1.66
    ↵
    1.56
     so
    1.49
     comienza
    1.45
     comienzan
    1.45
     continúa
    1.45
     llegan
    1.43
     still
    1.41
    Activations Density 0.003%

    No Known Activations