© 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. 34-GEMMASCOPE-RES-131K
    7. 57894
    Prev
    Next
    INDEX
    Explanations

    names starting with Earl

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

    This neuron specifically detects occurrences of the proper name “Earl.”

    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
     такі
    -0.86
    歳の
    -0.85
     bestätigen
    -0.84
    さび
    -0.82
    <0xBC>
    -0.82
     groans
    -0.82
     quyền
    -0.77
    麻煩
    -0.77
    幫
    -0.73
     ظرفیت
    -0.73
    POSITIVE LOGITS
    IER
    0.93
     Sweatshirt
    0.87
    垮
    0.80
     GREY
    0.79
    ear
    0.78
    ɞ
    0.78
     Earl
    0.76
    ier
    0.76
     Ear
    0.75
     teş
    0.75
    Activations Density 0.012%

    No Known Activations