© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50419
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and web references

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

    This neuron fires on programming‐ or markup‐related tokens—e.g. code keywords, package or command names, file extensions, and other technical identifiers.

    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
     Erfolge
    -0.84
    機關
    -0.76
    cox
    -0.75
     酒店
    -0.73
    ✬
    -0.71
    癀
    -0.71
    ówczas
    -0.70
    ACCEPTED
    -0.70
     Preferred
    -0.70
     älteren
    -0.70
    POSITIVE LOGITS
    hyper
    1.06
     hyper
    1.05
    uchten
    1.02
     backlinks
    0.97
     clickable
    0.92
    Cite
    0.87
     URLs
    0.87
    ısında
    0.87
     rematch
    0.85
     hyperlink
    0.85
    Activations Density 0.001%

    No Known Activations