© 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. 34-GEMMASCOPE-RES-131K
    7. 117868
    Prev
    Next
    INDEX
    Explanations

    mockingbird piggybacking laughing stock

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

    The neuron strongly fires on words ending in “-ing” (i.e. present participles/gerunds).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    yil
    -0.73
    ził
    -0.69
    を外
    -0.68
    fé
    -0.68
    的原因
    -0.67
    ANTIC
    -0.66
    hiya
    -0.65
     WASHINGTON
    -0.64
    inz
    -0.64
     Cana
    -0.64
    POSITIVE LOGITS
    jay
    1.09
    bird
    0.94
    JAY
    0.80
    oreille
    0.74
    bone
    0.74
    META
    0.72
    坪
    0.72
     Dick
    0.69
     zij
    0.69
    Rams
    0.69
    Activations Density 0.037%

    No Known Activations