© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41230
    Prev
    Next
    INDEX
    Explanations

    yes or no

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

    This neuron detects binary “yes/no” choice options, i.e. occurrences of “yes” or “no” presented as alternatives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     we
    -1.85
    犄
    -1.71
     股份
    -1.55
     июня
    -1.53
     нај
    -1.52
    Seventh
    -1.49
     gustado
    -1.48
    ishw
    -1.45
     AFTER
    -1.45
     ноября
    -1.44
    POSITIVE LOGITS
    This
    2.08
    There
    1.89
    They
    1.87
    "
    1.73
    It
    1.68
    惩
    1.67
    ,
    1.52
    That
    1.52
     będziemy
    1.48
    airobi
    1.45
    Activations Density 0.019%

    No Known Activations