© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75486
    Prev
    Next
    INDEX
    Explanations

    loud, loudly, aloud

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

    The neuron activates on words and forms denoting speaking or sound at high volume (e.g., loud, loudly, aloud, out loud).

    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
     may
    -2.03
    as
    -1.98
    and
    -1.95
     that
    -1.92
     these
    -1.89
     have
    -1.85
    that
    -1.82
     says
    -1.77
    there
    -1.71
    oh
    -1.69
    POSITIVE LOGITS
    厹
    2.25
    部分を
    1.94
    丝毫
    1.82
    ſtre
    1.74
     เปิด
    1.73
    颏
    1.62
    wendig
    1.62
    部分は
    1.59
     adhesivo
    1.59
     ambitions
    1.55
    Activations Density 0.001%

    No Known Activations