© 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. 72711
    Prev
    Next
    INDEX
    Explanations

    taken/given + outcome

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

    The neuron fires on past‐participle verbs (especially common ones like “taken” and “given”), signaling passive‐voice or perfect‐aspect constructions.

    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
    e
    -2.86
    寕
    -2.73
    y
    -2.63
    l
    -2.36
    8
    -2.27
    licious
    -2.22
    
    -2.22
    i
    -2.09
    ternut
    -2.05
    owment
    -2.03
    POSITIVE LOGITS
     пять
    2.13
     you
    2.11
     десять
    2.02
     oldukça
    2.00
     .
    2.00
     detaylı
    1.94
    )
    1.89
    觊
    1.89
     способ
    1.88
    蠵
    1.85
    Activations Density 0.012%

    No Known Activations