© 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. 71557
    Prev
    Next
    INDEX
    Explanations

    conditional code structure

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

    The neuron activates on the branching keyword “else” in code.

    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
     both
    -1.68
     their
    -1.68
     even
    -1.46
     just
    -1.45
     this
    -1.45
     which
    -1.36
     get
    -1.33
     begin
    -1.33
     from
    -1.30
     not
    -1.30
    POSITIVE LOGITS
     gänzlich
    1.30
     geschützt
    1.28
     vorne
    1.23
    際に
    1.21
     geprüft
    1.20
     เมื่อ
    1.18
     angepasst
    1.17
     trám
    1.16
    Descriere
    1.13
    naio
    1.12
    Activations Density 0.001%

    No Known Activations