© 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. 71373
    Prev
    Next
    INDEX
    Explanations

    section headings

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

    The neuron fires on standalone numeral tokens—i.e. isolated numbers (digits) used as headings, counts, or list markers.

    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
     époux
    -1.55
     siè
    -1.52
    ейчас
    -1.51
    楦
    -1.51
     estadounid
    -1.49
     Bakter
    -1.49
    tront
    -1.48
     blessés
    -1.46
     nieuwe
    -1.45
     kolik
    -1.42
    POSITIVE LOGITS
     and
    2.11
     not
    1.71
     re
    1.67
     may
    1.65
     used
    1.64
     Other
    1.63
     Before
    1.61
     frequently
    1.61
    </h2>
    1.59
     h
    1.59
    Activations Density 0.006%

    No Known Activations