© 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. 34-GEMMASCOPE-RES-131K
    7. 91561
    Prev
    Next
    INDEX
    Explanations

    disable, suppress, ignore, pragma

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

    This neuron fires on standalone numeric codes (e.g. version numbers or rule‐ID numbers) in pragmas or annotations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     unten
    -0.86
    讃
    -0.86
    cuela
    -0.85
    <0xC9>
    -0.82
    所需的
    -0.78
    特的
    -0.75
    autoload
    -0.75
    ,
    -0.75
    邻居
    -0.74
    insegna
    -0.73
    POSITIVE LOGITS
     حالت
    0.92
    blé
    0.91
     calda
    0.90
    zá
    0.87
    Ե
    0.85
    ！！
    0.85
    ñado
    0.84
     hadapan
    0.83
     Memper
    0.83
    所有
    0.83
    Activations Density 0.003%

    No Known Activations