© 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. 10-GEMMASCOPE-RES-131K
    7. 13789
    Prev
    Next
    INDEX
    Explanations

    variable assignment and initialization

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

    This neuron responds to 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_10/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
    6
    -2.17
    3
    -2.06
    5
    -2.00
    9
    -1.91
    4
    -1.66
    2
    -1.54
     reflejo
    -1.53
     volverá
    -1.51
    7
    -1.48
    即使
    -1.45
    POSITIVE LOGITS
    ↵
    1.75
     we
    1.71
     you
    1.53
     they
    1.43
     which
    1.38
     previamente
    1.38
     latter
    1.29
    の流れ
    1.26
    ibility
    1.23
     σελ
    1.23
    Activations Density 0.028%

    No Known Activations