© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38457
    Prev
    Next
    INDEX
    Explanations

    section titles or introductions

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

    This neuron detects section or chapter headings (e.g. table of contents entries and section titles) across various formats and languages.

    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
    ^(-
    -1.08
    Elaboración
    -1.08
     by
    -1.05
    Những
    -1.05
     their
    -1.04
     була
    -1.02
     most
    -1.02
     Many
    -1.02
    子さん
    -1.00
     masyarakat
    -0.98
    POSITIVE LOGITS
     précédent
    1.09
    曲が
    1.09
    tispiece
    0.99
    unate
    0.96
     exce
    0.96
     independente
    0.95
     vario
    0.94
    ruvate
    0.93
    兴奋
    0.93
     predicament
    0.92
    Activations Density 0.010%

    No Known Activations