© 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. 22-GEMMASCOPE-RES-131K
    7. 38872
    Prev
    Next
    INDEX
    Explanations

    code fragments and keywords

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

    The neuron strongly activates on programming–language keywords and instructions (e.g. mov, set, EXTERN, DEFINE, ALIGN, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    kosť
    -1.34
     previsão
    -1.24
     tradição
    -1.22
     Consejos
    -1.21
     promoção
    -1.20
    */
    -1.16
     cópia
    -1.16
    itada
    -1.15
     redução
    -1.14
     conclusão
    -1.14
    POSITIVE LOGITS
     have
    1.27
    le
    1.23
    ,
    1.16
     doesn
    1.13
     in
    1.09
    肖
    1.09
     one
    1.08
    ly
    1.07
     would
    1.02
     said
    1.02
    Activations Density 0.007%

    No Known Activations