© 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. 90714
    Prev
    Next
    INDEX
    Explanations

    electronic devices and equipment

    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
    L
    -1.67
    (
    -1.66
    c
    -1.65
    d
    -1.59
    F
    -1.57
     four
    -1.52
    W
    -1.52
    s
    -1.47
    ين
    -1.47
     if
    -1.46
    POSITIVE LOGITS
     is
    1.95
     lautet
    1.79
     discer
    1.77
    those
    1.68
     to
    1.66
     REALLY
    1.63
    COCK
    1.62
     unceasing
    1.62
     basierend
    1.61
    iterranée
    1.60
    Activations Density 1.302%

    No Known Activations