© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70729
    Prev
    Next
    INDEX
    Explanations

    true or false boolean logic

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

    The neuron detects occurrences of boolean literal tokens (e.g. “true” or “false”).

    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
     it
    -1.09
     resultar
    -1.08
    なのだ
    -1.02
    aiso
    -0.99
     masculinos
    -0.98
    }{}
    -0.97
    ㅗ
    -0.97
     masaje
    -0.95
    hangi
    -0.95
    ılmaz
    -0.94
    POSITIVE LOGITS
     sämtliche
    1.04
    Interes
    0.96
    Ingredienti
    0.96
     Kedua
    0.94
    𝑢
    0.90
    IES
    0.90
    Otras
    0.89
     biggest
    0.87
    Etimología
    0.87
    봤
    0.86
    Activations Density 0.001%

    No Known Activations