© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66806
    Prev
    Next
    INDEX
    Explanations

    statutory abuse filing principal definition

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

    This neuron activates on apostrophes marking possession (the genitive ’ or ’s in legal and formal texts).

    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
     who
    -1.70
     only
    -1.60
     mariée
    -1.55
     createSprite
    -1.45
    vább
    -1.45
     estructuras
    -1.43
    ytick
    -1.41
    Види
    -1.40
     récompense
    -1.38
    Durante
    -1.38
    POSITIVE LOGITS
     and
    2.14
    ↵
    1.77
    s
    1.67
     publice
    1.63
     use
    1.58
    却被
    1.41
     zove
    1.38
    蹀
    1.33
     kleinere
    1.33
     newest
    1.33
    Activations Density 0.058%

    No Known Activations