© 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. 22-GEMMASCOPE-RES-131K
    7. 73312
    Prev
    Next
    INDEX
    Explanations

    Code questions and structure

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

    The neuron fires on programming‐style identifiers and type names (e.g. class, ArrayList, Phone, Person) and other code tokens.

    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
    okra
    -1.14
     verbeteren
    -1.10
     '
    -1.04
     |
    -1.03
    TokenNameDOT
    -1.02
     vaikka
    -1.01
     Sub
    -1.00
    nefs
    -1.00
    ">(</
    -0.98
     aseguran
    -0.97
    POSITIVE LOGITS
    Caratteristiche
    1.36
     Terkait
    1.34
     nuova
    1.30
     neuesten
    1.27
     Pemain
    1.23
    ₤
    1.22
     tyto
    1.22
     goof
    1.20
     specchio
    1.19
    Răsp
    1.14
    Activations Density 0.000%

    No Known Activations