© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15637
    Prev
    Next
    INDEX
    Explanations

    int(

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

    The neuron strongly activates on occurrences of the standalone data‐type name “int” (in any casing or variation such as Int32).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     інте
    0.81
     intégr
    0.76
     Inte
    0.73
     интегра
    0.71
    getInt
    0.70
     integrals
    0.69
     ∫
    0.69
     passione
    0.69
     Bauern
    0.67
     INTEGER
    0.66
    POSITIVE LOGITS
    ว่าจะ
    0.55
     같다
    0.53
    불
    0.51
     불
    0.50
    AR
    0.50
    ไม่
    0.50
    와
    0.50
    митри
    0.49
    )$}
    0.49
    ക്ക
    0.49
    Activations Density 0.000%

    No Known Activations