© 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. 30800
    Prev
    Next
    INDEX
    Explanations

    code file types or programming terms

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

    This neuron detects domain-specific technical terms or metadata labels—typically nouns denoting object properties (e.g. APIs, discovered, diameter, ecliptic, days, Jupiter).

    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
    िल
    -0.70
    UML
    -0.67
     Gabor
    -0.65
    zlich
    -0.65
    ต้อง
    -0.65
    覚
    -0.63
     barrels
    -0.63
    ield
    -0.61
     mist
    -0.60
     Mist
    -0.60
    POSITIVE LOGITS
    それも
    0.73
    ドキュ
    0.70
    upassen
    0.69
     nyug
    0.68
     }}}{
    0.67
    ิ้ง
    0.67
     néhány
    0.66
    crop
    0.65
    Featuring
    0.65
     három
    0.64
    Activations Density 0.047%

    No Known Activations