© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10331
    Prev
    Next
    INDEX
    Explanations

    body limbs and their conditions

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

    body parts, particularly legs, arms, and thighs, in anatomical or medical contexts.

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

    the neuron detects mentions of body parts (especially limbs like “leg,” “legs,” “arm,” and “thighs”).

    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
    榀
    -1.65
     unsur
    -1.61
    FontAwesomeIcon
    -1.54
    Their
    -1.48
    </b>
    -1.45
     dozen
    -1.42
     haven
    -1.41
     scrit
    -1.38
    НЫЕ
    -1.36
    
    -1.35
    POSITIVE LOGITS
                
    1.95
    f
    1.77
     ihe
    1.75
     včetně
    1.74
    ৢ
    1.73
    z
    1.72
    まずは
    1.71
     indelible
    1.64
    ⎆
    1.63
    !"
    1.61
    Activations Density 0.059%

    No Known Activations