© 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. 63614
    Prev
    Next
    INDEX
    Explanations

    ANY KIND

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

    The neuron fires on the boilerplate text of open-source software licenses (e.g. “use… in source and binary forms,” “without warranties,” copyright years).

    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
     being
    -0.85
    덕
    -0.79
     speł
    -0.79
     Consulta
    -0.77
     gef
    -0.75
     quale
    -0.75
     kapag
    -0.74
     fulfilled
    -0.73
     sani
    -0.72
     sii
    -0.72
    POSITIVE LOGITS
    τυχ
    0.88
    Gadget
    0.85
    ъм
    0.82
    嵜
    0.80
    Bahkan
    0.77
     kter
    0.77
     exit
    0.77
     فيها
    0.77
    tedì
    0.77
    ("$.
    0.77
    Activations Density 0.001%

    No Known Activations