© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93285
    Prev
    Next
    INDEX
    Explanations

    return statements and code punctuation

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

    The neuron activates on numeric literals in code, highlighting tokens that consist of digits.

    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
    _
    -1.52
    A
    -1.45
    '
    -1.41
    #
    -1.40
    N
    -1.39
    I
    -1.38
    g
    -1.36
    P
    -1.34
    z
    -1.30
    D
    -1.29
    POSITIVE LOGITS
    Ár
    1.33
    ☡
    1.27
    nước
    1.25
    bzw
    1.18
    Karakter
    1.17
    ytu
    1.17
    Keterangan
    1.17
    Elekt
    1.16
    Elektron
    1.16
    Kritik
    1.15
    Activations Density 0.006%

    No Known Activations