© 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. 57544
    Prev
    Next
    INDEX
    Explanations

    tinnitus, ringing, hearing loss

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

    The neuron detects mentions of the medical condition “tinnitus” (persistent ringing in the ears).

    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
    jointed
    -0.67
     الري
    -0.67
    toupper
    -0.66
    ]!
    -0.66
     kiek
    -0.66
    showcase
    -0.65
     замо
    -0.65
     onCancelled
    -0.64
     trái
    -0.63
     força
    -0.63
    POSITIVE LOGITS
     ringing
    2.64
     tinnitus
    2.55
    ringing
    1.80
     Tin
    1.68
     buzzing
    1.52
    nitus
    1.48
    Tin
    1.46
     Ring
    1.42
    Ring
    1.36
    tin
    1.25
    Activations Density 0.042%

    No Known Activations