© 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. 10-GEMMASCOPE-RES-131K
    7. 8354
    Prev
    Next
    INDEX
    Explanations

    card-related phrases

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

    The neuron specializes in spotting hyphenated compounds that begin with “card-.”

    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
    ↵
    -2.23
    ,
    -1.90
    硨
    -1.84
    哒
    -1.77
    cinoma
    -1.76
    </h5>
    -1.75
    ALLENGES
    -1.73
     étanche
    -1.70
    а
    -1.70
    .
    -1.67
    POSITIVE LOGITS
    \%,
    1.97
    imantan
    1.95
     jeweiligen
    1.95
     становится
    1.92
     transforms
    1.92
     seminal
    1.79
    います
    1.78
    睏
    1.77
    에는
    1.77
     melalui
    1.76
    Activations Density 0.018%

    No Known Activations