© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95684
    Prev
    Next
    INDEX
    Explanations

    section headings or introductions

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

    This neuron detects major section or chapter headings (e.g. numbered or all-caps titles) in a document.

    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
    erweise
    -1.13
     desapar
    -1.05
    
    -1.04
    浃
    -1.03
    はもちろん
    -1.02
    داری
    -1.02
     används
    -1.02
    these
    -1.02
    Dichloropropene
    -1.01
     égard
    -0.99
    POSITIVE LOGITS
     and
    2.05
    </h2>
    1.10
    liston
    1.01
     Other
    1.01
    💸
    0.94
    พาะ
    0.94
    licó
    0.93
    </h3>
    0.92
     potem
    0.91
    ₹
    0.91
    Activations Density 0.033%

    No Known Activations