© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 417
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

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

    The neuron fires on code tokens that signal function or method calls—e.g. identifiers followed by “(…)” or “.method(…)” invocation patterns.

    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
    なので
    -1.26
     maravilhoso
    -1.23
    香り
    -1.21
     roxo
    -1.18
     chamado
    -1.17
     traseiro
    -1.13
    味わい
    -1.12
     feltro
    -1.11
     edifício
    -1.11
     personagem
    -1.10
    POSITIVE LOGITS
     and
    1.67
     or
    1.44
     này
    1.22
     This
    1.15
    It
    1.02
    Américaine
    1.01
    fordshire
    1.00
     like
    1.00
     what
    1.00
     this
    0.99
    Activations Density 0.685%

    No Known Activations