© 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. 34199
    Prev
    Next
    INDEX
    Explanations

    assigning variables in code

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

    This neuron detects numeric literals (standalone numbers) in code snippets.

    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
     целом
    -1.14
    ilación
    -1.04
     различных
    -1.04
    どうやら
    -1.04
     klassischen
    -1.03
     różnych
    -1.00
     stří
    -0.96
     различни
    -0.95
     literaria
    -0.94
     verschiedenen
    -0.94
    POSITIVE LOGITS
     those
    1.09
     with
    1.09
     by
    0.99
     from
    0.95
    渝
    0.94
    ǧ
    0.94
    AGI
    0.93
     and
    0.93
     when
    0.92
    ∎
    0.91
    Activations Density 0.001%

    No Known Activations