© 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. 10-GEMMASCOPE-RES-131K
    7. 43000
    Prev
    Next
    INDEX
    Explanations

    code syntax and file paths

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

    This neuron fires on uppercase or CamelCase code identifiers and file-type acronyms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     what
    -1.55
    лятор
    -1.34
     sedia
    -1.31
     nini
    -1.27
     morto
    -1.26
     andato
    -1.23
     bagay
    -1.22
    BatchNorm
    -1.20
     are
    -1.20
     borsa
    -1.20
    POSITIVE LOGITS
     clicar
    1.40
     Якщо
    1.28
    :"
    1.26
     Шаг
    1.26
     complejos
    1.20
     requiere
    1.19
     Veränder
    1.19
     Abweich
    1.18
     previamente
    1.18
     trabajadores
    1.18
    Activations Density 0.272%

    No Known Activations