© 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. 112767
    Prev
    Next
    INDEX
    Explanations

    sporadic medical conditions

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

    The neuron detects the word "sporadic" and related forms, particularly when describing medical conditions or occurrences.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    </strong>
    -2.64
    י
    -2.33
    ان
    -2.28
     they
    -2.19
    य
    -2.16
    
    -2.11
    艽
    -2.08
     französ
    -2.08
    posure
    -2.05
     Architekt
    -2.03
    POSITIVE LOGITS
    鶿
    2.64
    she
    2.38
     /**
    2.30
    ть
    2.28
    ꪻ
    2.25
    ̖
    2.20
     grinning
    2.19
     suffoc
    2.14
    蜑
    2.13
    stood
    2.11
    Activations Density 0.061%

    No Known Activations