© 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. 128938
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily fires on numeric literals (digit sequences) in the markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    html src attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     if
    -1.24
     have
    -1.19
     this
    -1.15
     its
    -1.14
    For
    -1.12
     started
    -1.12
     any
    -1.09
    an
    -1.09
     anything
    -1.08
     having
    -1.07
    POSITIVE LOGITS
     maravill
    1.30
     Reſ
    1.22
     zatem
    1.21
     colgantes
    1.20
     ܗ
    1.19
     espectaculares
    1.19
     Perſ
    1.18
    Reviewed
    1.18
    鲼
    1.17
     wó
    1.16
    Activations Density 0.004%

    No Known Activations