© 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. 34-GEMMASCOPE-RES-131K
    7. 117263
    Prev
    Next
    INDEX
    Explanations

    code imports and declarations

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

    This neuron fires on numeric literal tokens (i.e. 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_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
     platelets
    -0.83
     Serialize
    -0.79
    ūras
    -0.78
     angele
    -0.77
     Arya
    -0.74
    려
    -0.73
     simbol
    -0.73
    melan
    -0.72
     '}
    -0.72
    izable
    -0.72
    POSITIVE LOGITS
    SFER
    0.78
     CIM
    0.77
    合併
    0.75
    upuncture
    0.74
     liberally
    0.74
    ciuta
    0.72
     nouveautés
    0.72
    ⁕
    0.71
     Amherst
    0.71
    出版社
    0.71
    Activations Density 0.000%

    No Known Activations