© 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. 41443
    Prev
    Next
    INDEX
    Explanations

    ear and otitis media

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

    medical terminology related to the ear and hearing, including conditions, anatomical structures, and disorders affecting the auditory system.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects ear-related anatomical or clinical terms (e.g. “otic,” “ear,” “aural,” “otitis,” “sensorineural,” etc.).

    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
    7
    -1.31
    s
    -1.25
    !(:
    -1.23
     helst
    -1.14
     веществ
    -1.10
     ungefähr
    -1.08
     skydd
    -1.08
    釭
    -1.06
    3
    -1.06
     fört
    -1.06
    POSITIVE LOGITS
     ear
    1.73
    }
    1.50
     Ohren
    1.45
    >
    
    
    1.31
     appuntamento
    1.28
    GGT
    1.27
     phone
    1.26
    }$,
    1.25
     headphones
    1.24
    を紹介します
    1.24
    Activations Density 0.109%

    No Known Activations