© 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. 78424
    Prev
    Next
    INDEX
    Explanations

    if defined compiler directives

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

    The neuron strongly responds to C/C++ preprocessor directives (especially conditional directives like “#if,” “defined(…),” “#else,” and related 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_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
    registrer
    -0.96
     pièce
    -0.96
    Kamera
    -0.91
    濯
    -0.90
    してほしい
    -0.88
    Schon
    -0.88
    Ново
    -0.88
    𝒦
    -0.86
    Проце
    -0.84
    цію
    -0.84
    POSITIVE LOGITS
     defined
    2.44
    defined
    1.99
    Defined
    1.38
     define
    1.30
     !
    1.29
     Defined
    1.22
     défin
    1.20
     Define
    1.16
    !
    1.13
     definido
    1.07
    Activations Density 0.021%

    No Known Activations