© 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. 22-GEMMASCOPE-RES-131K
    7. 35003
    Prev
    Next
    INDEX
    Explanations

    function closing delimiters

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

    The neuron strongly fires on numeric and boolean literals (e.g. numbers like “1990”, “0.2175”, integer constants, “true”, “false”, etc.).

    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
     had
    -1.09
    setMode
    -1.02
     while
    -0.99
    ϫ
    -0.98
    ně
    -0.98
     Only
    -0.95
     may
    -0.94
     was
    -0.93
     although
    -0.93
     probably
    -0.93
    POSITIVE LOGITS
    或者是
    1.11
    ḿ
    1.06
    不上
    1.04
     потім
    1.02
    gefügt
    1.01
    ülle
    1.01
    elit
    1.01
    BACA
    0.96
     וגם
    0.96
    ברו
    0.96
    Activations Density 0.005%

    No Known Activations