© 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. 10-GEMMASCOPE-RES-131K
    7. 12691
    Prev
    Next
    INDEX
    Explanations

    integer variable declaration

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

    The neuron is essentially detecting occurrences of integer‐type tokens (e.g. “int” or “Integer”) 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_10/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
    вгений
    -2.09
     continúas
    -2.06
     parfü
    -2.05
     anuncia
    -2.02
     annons
    -1.98
    Spesifikasi
    -1.97
     varmt
    -1.95
    امکان
    -1.94
     lanza
    -1.91
     ingenting
    -1.89
    POSITIVE LOGITS
     from
    2.70
     Also
    2.11
     with
    2.11
     also
    2.06
    </h3>
    2.02
     most
    2.02
     only
    1.96
     all
    1.92
     to
    1.91
     on
    1.90
    Activations Density 0.015%

    No Known Activations