© 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. 41295
    Prev
    Next
    INDEX
    Explanations

    analysis of research methods

    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
     even
    -2.05
     chré
    -2.03
     will
    -2.02
     of
    -1.82
     still
    -1.70
     الجلد
    -1.70
    Médaille
    -1.63
     so
    -1.61
     with
    -1.55
     meningkat
    -1.52
    POSITIVE LOGITS
    וּ
    2.25
     бампер
    2.23
     кроссовки
    1.79
    ִּ
    1.78
    ֶּ
    1.73
    ּוֹ
    1.69
    ַּ
    1.61
    ְּ
    1.59
    ᾿
    1.59
    ᾽
    1.54
    Activations Density 0.156%

    No Known Activations