© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84360
    Prev
    Next
    INDEX
    Explanations

    beginnings

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

    The neuron responds to major section titles or headings 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
     سگ
    -0.96
    both
    -0.93
    banners
    -0.90
     neither
    -0.90
     opzioni
    -0.89
     czasem
    -0.88
    solicit
    -0.88
    <bos>
    -0.88
     both
    -0.88
     formie
    -0.88
    POSITIVE LOGITS
     with
    1.98
     on
    1.21
    чать
    1.16
     start
    1.13
     at
    1.12
     starts
    1.00
     начать
    0.99
     countdown
    0.98
    cycle
    0.95
    ênero
    0.92
    Activations Density 0.088%

    No Known Activations