© 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. 34-GEMMASCOPE-RES-131K
    7. 31519
    Prev
    Next
    INDEX
    Explanations

    physical arrangement and connections

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

    This neuron responds to the dense, highly technical, patent‐style specification language used in formal device and mechanism descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     wielu
    -0.95
    Interactor
    -0.94
    weebly
    -0.91
     líqu
    -0.90
     bílá
    -0.89
     TÉCN
    -0.87
    bemos
    -0.86
    Página
    -0.85
    Folge
    -0.85
    
    -0.84
    POSITIVE LOGITS
     embodiments
    1.20
     plural
    1.08
    藉
    1.02
     FIG
    1.02
    hereinafter
    1.01
     Plural
    0.94
     plurality
    0.92
     hereinafter
    0.90
     teachings
    0.88
    plural
    0.88
    Activations Density 1.204%

    No Known Activations