© 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. 34-GEMMASCOPE-RES-131K
    7. 93442
    Prev
    Next
    INDEX
    Explanations

    code blocks and programming definitions

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

    The neuron fires on Boolean “or” operations in code (both the word `or` and the symbol `||`).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    certainly
    -1.45
    鵙
    -1.41
     anún
    -1.41
    definitely
    -1.39
     rése
    -1.35
     itinéraire
    -1.35
     camiset
    -1.34
     collè
    -1.33
     diriger
    -1.33
    Ꮞ
    -1.31
    POSITIVE LOGITS
     !
    1.99
     (
    1.49
     but
    1.42
     in
    1.41
     there
    1.35
    !
    1.23
     !!
    1.19
     it
    1.16
    !)
    1.12
     !(
    1.11
    Activations Density 0.003%

    No Known Activations