© 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. 73762
    Prev
    Next
    INDEX
    Explanations

    headings followed by colon

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

    The neuron detects standalone page or document section headings (single-word titles like “Specifications,” “Features,” “Account,” “Plans,” 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_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
     sumptuous
    -1.08
    lové
    -1.07
     …
    -1.02
    ini
    -1.00
     hugely
    -1.00
     IMPLEMENTATION
    -0.99
     棚
    -0.98
     сообщает
    -0.98
     新品
    -0.97
    ger
    -0.97
    POSITIVE LOGITS
    </h2>
    1.66
    '},
    
    1.17
    ebvre
    1.15
    Какие
    1.14
     bús
    1.12
     biela
    1.12
    ficamente
    1.11
    beda
    1.11
    Other
    1.09
     歳
    1.08
    Activations Density 0.020%

    No Known Activations