© 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. 78109
    Prev
    Next
    INDEX
    Explanations

    int main()

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

    The neuron strongly activates on the substring “int” (e.g. the keyword `int` itself or any token containing “int,” such as `romanToInt`).

    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
    ‌.
    -0.97
     (~(
    -0.90
    ẹn
    -0.90
    ttää
    -0.86
    nejšie
    -0.83
    短暂
    -0.82
    所说
    -0.82
     stolet
    -0.82
    快速的
    -0.81
    trauer
    -0.81
    POSITIVE LOGITS
    *
    1.25
    1.16
     ランド
    1.13
     compare
    1.09
    \&
    1.09
     main
    1.08
    *

    1.07
    						
    1.05
     **
    1.03
    **
    1.02
    Activations Density 0.016%
    No Known Activations