© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86820
    Prev
    Next
    INDEX
    Explanations

    constructor calls

    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
    蛲
    -1.59
    greja
    -1.52
     trám
    -1.47
     nowy
    -1.46
     sánh
    -1.44
     dirigeants
    -1.42
     estudo
    -1.37
     exposiciones
    -1.37
     miasto
    -1.33
     campañas
    -1.33
    POSITIVE LOGITS
    The
    2.03
    There
    1.75
    1
    1.66
    0
    1.63
    This
    1.61
    e
    1.53
    8
    1.52
    though
    1.45
    These
    1.45
    Although
    1.44
    Activations Density 0.004%

    No Known Activations