© 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. 40023
    Prev
    Next
    INDEX
    Explanations

    no single

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

    The neuron strongly activates on abstract, formal nouns and quantifier terms (like “reason,” “responsibility,” “source,” “single/any/no,” etc.) that structure arguments or statements of duty.

    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
    sometimes
    -1.25
    cuando
    -0.97
     nästan
    -0.97
     fortfarande
    -0.93
    pagnole
    -0.93
    ajaja
    -0.93
     först
    -0.92
    ڧ
    -0.91
    chsel
    -0.91
     kwiaty
    -0.90
    POSITIVE LOGITS
     specific
    2.30
     particular
    2.13
     individual
    1.85
     конкре
    1.76
    特定
    1.64
     single
    1.55
    specific
    1.45
     específico
    1.45
    Specific
    1.45
     einzelnen
    1.39
    Activations Density 0.062%

    No Known Activations