© 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. 10-GEMMASCOPE-RES-131K
    7. 101619
    Prev
    Next
    INDEX
    Explanations

    Clair and pathology

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

    names with "Clair" or "Sinclair" and words related to medical pathology.

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

    This neuron strongly responds to occurrences of the five‐letter substring “clair” (as in Clair, Sinclair, Éclair, Montclair) in tokens.

    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
    缡
    -3.05
    塍
    -2.44
    われています
    -2.44
    昻
    -2.42
    辚
    -2.36
    !’
    -2.34
     abſ
    -2.30
    呖
    -2.28
    猜测
    -2.25
    方才
    -2.25
    POSITIVE LOGITS
    大概
    3.36
    It
    2.92
    ’
    2.77
     '
    2.70
     selben
    2.67
    ',
    2.61
    }
    2.59
    他
    2.55
    {
    2.53
    使用
    2.45
    Activations Density 0.004%

    No Known Activations