© 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. 10-GEMMASCOPE-RES-131K
    7. 70610
    Prev
    Next
    INDEX
    Explanations

    pages, punctuation

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

    This neuron detects page‐number references in bibliographic entries (e.g. the “p” in “p. 312” or similar).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     not
    -1.77
     our
    -1.55
     then
    -1.52
     другим
    -1.48
    Semitism
    -1.45
     when
    -1.41
     being
    -1.41
     as
    -1.39
     with
    -1.38
    
    -1.38
    POSITIVE LOGITS
     "
    1.53
     :"
    1.45
     -"
    1.41
     availa
    1.34
    --"
    1.32
    ⸻
    1.30
    beyaz
    1.30
     "...
    1.29
    ："
    1.27
    2
    1.25
    Activations Density 0.019%

    No Known Activations