© 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. 10-GEMMASCOPE-RES-131K
    7. 127819
    Prev
    Next
    INDEX
    Explanations

    inhibitor, agent, disease

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

    commas following technical or scientific terms, especially when describing compounds, agents, or organizations.

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

    The neuron detects words immediately preceding numerical values or quantitative measurements.

    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
    ሖ
    -1.53
    轳
    -1.49
    嗵
    -1.47
     beantragt
    -1.38
     quiero
    -1.38
    褙
    -1.37
    不去
    -1.37
    ౬
    -1.36
     gewähr
    -1.34
     comodo
    -1.34
    POSITIVE LOGITS
     and
    2.41
     still
    2.00
     by
    1.80
     on
    1.73
    ↵↵
    1.63
     at
    1.58
     from
    1.48
     while
    1.26
     in
    1.26
    ↵↵↵
    1.24
    Activations Density 0.107%

    No Known Activations