© 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. 28282
    Prev
    Next
    INDEX
    Explanations

    ordinal position

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

    This neuron fires on section‐or list‐heading tokens (the initial words of titles, subheadings, and numbered list items).

    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
     also
    -2.63
     and
    -1.87
     также
    -1.78
     також
    -1.75
     também
    -1.73
     również
    -1.67
     myös
    -1.66
     también
    -1.62
     Also
    -1.59
     भी
    -1.56
    POSITIVE LOGITS
     první
    1.30
     pierwszy
    1.28
    Firstly
    1.27
    が一番
    1.27
     primeiro
    1.27
     pierws
    1.21
    ఽ
    1.21
     først
    1.20
     første
    1.18
    Seems
    1.18
    Activations Density 0.050%

    No Known Activations