© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11833
    Prev
    Next
    INDEX
    Explanations

    hearing protection, ears, tinnitus

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

    The neuron fires on mentions of head‐and‐neck sensory organs and related medical/hearing terms (e.g. ears, hearing loss, ENT).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    regon
    0.59
    🍞
    0.55
    酆
    0.55
    腩
    0.54
     Chatham
    0.54
     homophobic
    0.52
     homosexuality
    0.51
    ्लादेश
    0.49
    婺
    0.49
     ট্রে
    0.49
    POSITIVE LOGITS
    耳
    2.48
     ear
    2.41
     耳
    2.38
     Ear
    2.25
    Ear
    2.22
     ears
    2.13
    耳朵
    2.11
     Ears
    2.06
     Hearing
    2.02
     hearing
    1.95
    Activations Density 0.246%

    No Known Activations