© 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. 22-GEMMASCOPE-RES-131K
    7. 16174
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

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

    The neuron fires on numeric literals (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
    珦
    -1.10
     your
    -1.06
    好处
    -1.03
    ınıza
    -1.03
    имущества
    -1.02
    paroles
    -1.02
     exitoso
    -1.00
    始めて
    -0.99
    会社の
    -0.99
     their
    -0.98
    POSITIVE LOGITS
     نیز
    1.24
     and
    1.21
    기도
    1.05
     折りたたみ
    0.97
     также
    0.97
     остается
    0.92
     médicaments
    0.91
     signif
    0.91
     たま
    0.91
    Also
    0.90
    Activations Density 0.000%

    No Known Activations