© 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. 34-GEMMASCOPE-RES-131K
    7. 63871
    Prev
    Next
    INDEX
    Explanations

    introduction, section, page, chapter

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

    The neuron detects numeric document identifiers—especially section, chapter, or problem numbers and other standalone numerals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     parlor
    -0.76
     parlour
    -0.75
    sendTo
    -0.74
     Verbre
    -0.74
    mName
    -0.74
    prede
    -0.73
    헨
    -0.72
    mState
    -0.71
     immediatamente
    -0.71
    久しぶり
    -0.70
    POSITIVE LOGITS
     textbook
    1.28
     section
    1.09
     Section
    1.09
     vocabulary
    1.02
     Sections
    1.01
     notes
    1.00
    Section
    0.97
     pages
    0.96
     sections
    0.95
     pg
    0.94
    Activations Density 0.033%

    No Known Activations