© 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. 10-GEMMASCOPE-RES-131K
    7. 100282
    Prev
    Next
    INDEX
    Explanations

    else code blocks

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

    the keyword "else" in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is detecting occurrences of the “else” keyword 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
    蜴
    -2.28
    了一個
    -2.03
    퐹
    -1.88
     як
    -1.83
    でしたが
    -1.79
     Fortsch
    -1.79
     tireless
    -1.75
     henceforth
    -1.74
     therefor
    -1.73
     décrit
    -1.72
    POSITIVE LOGITS
    else
    2.22
    狨
    2.16
    it
    2.13
    ⸥
    2.13
    橚
    2.11
     sneak
    2.00
    还能
    1.99
     italianos
    1.98
     paisajes
    1.98
     they
    1.98
    Activations Density 0.003%

    No Known Activations