© 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. 106683
    Prev
    Next
    INDEX
    Explanations

    interpolated variables or placeholders

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

    The neuron fires on numeric literal tokens (i.e. standalone digits or 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
    ("
    -1.24
    “
    -0.96
     a
    -0.95
    /'.$
    -0.92
    вшие
    -0.92
    }($
    -0.91
     (‘
    -0.90
     xấu
    -0.90
     “
    -0.86
     (“
    -0.86
    POSITIVE LOGITS
     ${
    1.23
     `${
    1.20
     {@
    1.14
     #{
    1.12
     <?
    1.02
     \(
    1.02
     $"{
    0.94
    ể
    0.93
     <?=
    0.93
     /></
    0.92
    Activations Density 0.023%

    No Known Activations