© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81254
    Prev
    Next
    INDEX
    Explanations

    sizeof ( type )

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

    This neuron activates on C/C++ type‐inspection and preprocessor keywords (e.g. sizeof, typeof, #ifdef, __GNUC__).

    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
     adjunct
    -0.98
    несен
    -0.85
     considérer
    -0.82
    вобо
    -0.82
     فشار
    -0.81
    providedIn
    -0.79
    zsef
    -0.79
    _{*
    -0.78
    Interment
    -0.77
    cić
    -0.77
    POSITIVE LOGITS
     triliun
    1.00
    )}=
    0.85
    절
    0.85
    милия
    0.83
     bukanlah
    0.82
     ESTABL
    0.81
    (
    0.81
     vasi
    0.81
     divisa
    0.80
     człowieka
    0.79
    Activations Density 0.004%

    No Known Activations