© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72341
    Prev
    Next
    INDEX
    Explanations

    document headings and titles

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

    This neuron detects section or document headings and titles (e.g. “Scope and Contents,” “Description of…,” “History of…,” etc.).

    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
    SequentialGroup
    -1.48
    
    -1.34
     【
    -1.33
    pherds
    -1.33
     キ
    -1.30
     ド
    -1.29
    wants
    -1.29
     douane
    -1.28
     sâ
    -1.28
    umenter
    -1.27
    POSITIVE LOGITS
    :
    1.92
     includes
    1.58
     new
    1.46
     about
    1.38
     según
    1.28
     including
    1.27
     почти
    1.26
    镯
    1.26
     incluso
    1.25
    stdafx
    1.25
    Activations Density 0.652%

    No Known Activations