© 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. 22-GEMMASCOPE-RES-131K
    7. 54267
    Prev
    Next
    INDEX
    Explanations

    retinal or retina

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

    words and phrases related to "retina" and ocular/eye terminology in medical and technical contexts.

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

    This neuron responds to occurrences of “ret” in biomedical terms, especially in words like retina or retinal.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ↵↵
    -2.61
    ac
    -2.25
    N
    -2.20
    卧槽
    -2.17
    atação
    -2.11
    ⬮
    -2.11
    in
    -2.06
    
    -2.06
    AN
    -2.03
    when
    -2.02
    POSITIVE LOGITS
     stelle
    2.58
    毟
    2.53
    ’
    2.50
     Teléfono
    2.34
    の作品
    2.33
    Ⴀ
    2.22
    HORE
    2.20
    "--
    2.20
    乀
    2.19
     bahwa
    2.17
    Activations Density 0.019%

    No Known Activations