© 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. 74884
    Prev
    Next
    INDEX
    Explanations

    version information

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

    The neuron fires on numeric identifiers in code comments—things like version numbers, revision or build numbers, and other digits in header annotations.

    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
    tığı
    -1.17
     of
    -1.13
     those
    -1.09
     why
    -1.09
     That
    -1.08
    太多的
    -1.05
     because
    -1.02
    慙
    -1.01
     terlebih
    -1.01
    Because
    -1.00
    POSITIVE LOGITS
     Version
    1.13
    chmod
    1.09
    Köln
    1.05
     partículas
    1.05
    chymal
    1.05
    version
    1.04
    ZZLE
    1.04
     version
    1.04
     версии
    1.03
    Adriana
    1.01
    Activations Density 0.013%

    No Known Activations