© 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. 22-GEMMASCOPE-RES-131K
    7. 75140
    Prev
    Next
    INDEX
    Explanations

    abbreviations and initialisms

    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_22/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
     mediodía
    -0.93
     grouped
    -0.90
     somewhat
    -0.88
    zumaki
    -0.86
    <0xB5>
    -0.85
     Ảnh
    -0.84
    呶
    -0.84
     éstos
    -0.84
     ottimo
    -0.84
    QUADS
    -0.84
    POSITIVE LOGITS
     burton
    0.93
    Agosto
    0.89
     üzerine
    0.84
    解説
    0.83
     Property
    0.79
    спорти
    0.79
     blumen
    0.77
    으로
    0.76
    GTP
    0.76
    PSG
    0.75
    Activations Density 0.056%

    No Known Activations