© 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. 71262
    Prev
    Next
    INDEX
    Explanations

    not continue

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on occurrences of the negation “not.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    einem
    -0.98
     frågor
    -0.93
     нев
    -0.93
    视着
    -0.91
    これも
    -0.90
    と思って
    -0.88
    арак
    -0.87
     tasa
    -0.86
    oucí
    -0.85
    Slime
    -0.85
    POSITIVE LOGITS
     anymore
    1.69
    ต่อไป
    0.98
    繼續
    0.96
     continue
    0.96
     ادامه
    0.93
     continued
    0.91
     continuar
    0.90
     weiterhin
    0.89
    īgas
    0.88
     продол
    0.85
    Activations Density 0.081%

    No Known Activations