© 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. 69516
    Prev
    Next
    INDEX
    Explanations

    neutral

    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
     perdiendo
    -2.02
     dejando
    -2.00
     Ive
    -1.91
     Besonder
    -1.83
     poniendo
    -1.82
    Зно
    -1.80
    imantan
    -1.79
     llevando
    -1.78
     languid
    -1.77
     Isto
    -1.76
    POSITIVE LOGITS
    It
    2.03
     neutral
    1.91
     peruano
    1.76
    "
    1.76
    er
    1.66
    There
    1.63
    at
    1.63
    izers
    1.60
    neutral
    1.59
    ‼
    1.52
    Activations Density 0.012%

    No Known Activations