© 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. 10-GEMMASCOPE-RES-131K
    7. 130386
    Prev
    Next
    INDEX
    Explanations

    Tacloban, Tacrine, Tacuba, Tacrolimus, Tacoma, Tic Tac Toe

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

    This neuron activates for "tac" when it appears in words or phrases like "Tic-Tac-Toe" or "tacrolimus" (a medical drug).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    쨩
    -2.78
    沄
    -2.77
     برای
    -2.69
    垕
    -2.59
    鉝
    -2.56
     If
    -2.50
    ㈰
    -2.44
     encontram
    -2.42
     جدید
    -2.39
    嚒
    -2.39
    POSITIVE LOGITS
    or
    3.00
    er
    2.83
     he
    2.66
    на
    2.64
    栳
    2.55
    ”
    2.45
    >
    2.41
    on
    2.41
    瓩
    2.41
    (
    2.38
    Activations Density 0.002%

    No Known Activations