© 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. 39278
    Prev
    Next
    INDEX
    Explanations

    mind blowing, psychedelic, Nolan

    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
    تفصیلات
    -1.45
     "}";
    -1.44
    usure
    -1.43
     geliefert
    -1.39
    もしくは
    -1.38
     qualcosa
    -1.35
     pisze
    -1.35
    empres
    -1.34
     esigen
    -1.34
     Pristup
    -1.33
    POSITIVE LOGITS
    .
    1.71
    ("
    1.61
    </em>
    1.56
     agora
    1.50
    呖
    1.47
     fête
    1.46
    db
    1.30
     employ
    1.29
    bind
    1.29
    f
    1.27
    Activations Density 0.046%

    No Known Activations