© 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. 19135
    Prev
    Next
    INDEX
    Explanations

    fetch data

    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
    𓐍
    -1.98
     ennemi
    -1.91
     như
    -1.91
    Ᏺ
    -1.91
    呖
    -1.84
    ؛
    -1.83
     sento
    -1.75
     literatura
    -1.74
     utilised
    -1.72
     fui
    -1.70
    POSITIVE LOGITS
     is
    2.23
     serán
    2.17
     empuj
    2.16
    さに
    2.00
     amenaz
    1.97
     entspre
    1.93
     fueran
    1.87
    řízen
    1.85
     They
    1.85
     deberán
    1.82
    Activations Density 0.018%

    No Known Activations