© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67129
    Prev
    Next
    INDEX
    Explanations

    return statements

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

    The neuron activates on integer literal tokens (stand-alone numbers) 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_22/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
    ことも
    -1.20
    のではないでしょうか
    -1.13
    の準備
    -1.10
     celana
    -1.09
    )}
    -0.99
    closedir
    -0.95
    おそ
    -0.95
     molte
    -0.95
    の概要
    -0.93
    ratis
    -0.93
    POSITIVE LOGITS
    毕竟
    0.96
     plethora
    0.96
    貴族
    0.96
    山中
    0.94
     trí
    0.94
     Péter
    0.93
     epitom
    0.93
    呖
    0.93
    leč
    0.91
    aughey
    0.90
    Activations Density 0.001%

    No Known Activations