© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7629
    Prev
    Next
    INDEX
    Explanations

    else keyword in code

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

    The main thing this neuron does is detect the keyword “else” in programming/conditional statements.

    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
    Ov
    0.64
    才
    0.63
    Denn
    0.63
    رود
    0.62
    揩
    0.62
    Rod
    0.59
    Travis
    0.59
    ブラン
    0.59
    Litt
    0.59
    atte
    0.58
    POSITIVE LOGITS
     if
    0.72
     medicare
    0.65
    iftoire
    0.64
     glTranslatef
    0.63
     idk
    0.63
     '';
    0.62
     ImportError
    0.62
     suede
    0.62
    vier
    0.61
     minSdkVersion
    0.61
    Activations Density 0.020%

    No Known Activations