© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16194
    Prev
    Next
    INDEX
    Explanations

    things, many, several, lots, a few

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

    The neuron consistently activates on the auxiliary verb “are.”

    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
    -2.19
    neling
    -1.93
    the
    -1.75
     effect
    -1.73
     which
    -1.71
    hiva
    -1.69
    In
    -1.68
    It
    -1.66
    p
    -1.66
    your
    -1.60
    POSITIVE LOGITS
     also
    2.41
     not
    2.02
     empezaron
    1.94
     few
    1.91
     judíos
    1.84
    
    1.83
     regarded
    1.78
     estuvieron
    1.77
    źródło
    1.73
    Bisous
    1.71
    Activations Density 0.038%

    No Known Activations