© 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. 22099
    Prev
    Next
    INDEX
    Explanations

    confirmed cases

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

    instances where a case or diagnosis has been confirmed in medical or scientific contexts.

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

    The neuron is selectively activating on numeric tokens—counts, measurements, and especially decimal or integer values appearing in the text.

    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
    桫
    -1.99
    釭
    -1.91
    嗔
    -1.87
    ⎔
    -1.86
    ࿊
    -1.80
    搋
    -1.78
    
    -1.77
    </h3>
    -1.76
     neler
    -1.74
    Practices
    -1.72
    POSITIVE LOGITS
    Many
    2.36
    Three
    2.28
    Now
    2.17
    Have
    2.16
    Other
    2.14
     confirmed
    2.13
    Get
    2.08
    Usually
    2.05
    Several
    2.02
    Still
    2.00
    Activations Density 0.020%

    No Known Activations