© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9003
    Prev
    Next
    INDEX
    Explanations

    else followed by ( or :

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

    The neuron fires on words that introduce the fallback branch in conditional logic (e.g. “else”/“otherwise”).

    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_24_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
    ER
    0.88
     evitar
    0.88
    Magg
    0.88
     thêm
    0.87
    ﺭ
    0.85
    ार
    0.85
     éviter
    0.84
    鿓
    0.84
    ﻕ
    0.83
    Spr
    0.82
    POSITIVE LOGITS
    ,
    0.97
     बिल्कुल
    0.77
    س
    0.77
    ="<?
    0.75
    ние
    0.73
    орга
    0.73
     (
    0.72
     sworn
    0.71
    ،
    0.71
    ース
    0.70
    Activations Density 0.000%

    No Known Activations