© 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. 73404
    Prev
    Next
    INDEX
    Explanations

    variable declaration

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

    This neuron detects code tokens that introduce or declare variables (e.g. “let,” “var,” “private,” “protected,” “$,” and similar binding keywords).

    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
    Ainda
    -1.16
    Mesmo
    -1.15
     because
    -1.12
     entweder
    -1.11
    ьере
    -1.09
     Ainda
    -1.09
     initView
    -1.07
    Даже
    -1.05
     Também
    -1.03
    Também
    -1.02
    POSITIVE LOGITS
     in
    1.15
     αὐτ
    1.00
     sauf
    1.00
    licherweise
    0.97
     courant
    0.96
     env
    0.94
    vost
    0.92
    mock
    0.92
    leyebilirsiniz
    0.89
    reck
    0.88
    Activations Density 0.003%

    No Known Activations