© 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. 68797
    Prev
    Next
    INDEX
    Explanations

    blood flow and patient triage

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

    names or anatomical terms with foreign or technical origins.

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

    The neuron responds to specialized technical or medical‐research terms—especially nouns denoting procedures, measurements, or pathological findings.

    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
    <bos>
    -2.92
    8
    -2.67
    </strong>
    -2.56
    O
    -2.56
    but
    -2.56
    S
    -2.55
    st
    -2.55
    6
    -2.48
    in
    -2.41
    m
    -2.34
    POSITIVE LOGITS
    ᯾
    2.70
    媗
    2.61
     piratas
    2.61
    ’
    2.55
    idemia
    2.50
    𖣔
    2.36
     entendi
    2.28
    ᚔ
    2.25
    </h2>
    2.25
    
    2.20
    Activations Density 0.105%

    No Known Activations