© 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. 22-GEMMASCOPE-RES-131K
    7. 13370
    Prev
    Next
    INDEX
    Explanations

    negation

    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_22/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
    というのも
    -1.03
    などが
    -0.96
     instead
    -0.93
    ХА
    -0.90
     Otra
    -0.88
    ade
    -0.83
    などを
    -0.83
     blessé
    -0.83
    それにしても
    -0.82
    despite
    -0.82
    POSITIVE LOGITS
     enfrent
    1.05
     additional
    1.00
    感じが
    0.98
    場所で
    0.94
     هیچ
    0.91
     plenamente
    0.91
    ところに
    0.90
     admitir
    0.88
     incluir
    0.88
    ดน
    0.88
    Activations Density 0.088%

    No Known Activations