© 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. 10-GEMMASCOPE-RES-131K
    7. 101954
    Prev
    Next
    INDEX
    Explanations

    section titles

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

    This neuron fires on Markdown-style section headings (lines beginning with one or more ‘#’).

    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
      
    -1.45
     a
    -1.45
    ↵↵↵
    -1.45
    er
    -1.41
     obicei
    -1.38
     all
    -1.37
    <
    -1.30
    </strong>
    -1.30
     always
    -1.30
    \
    -1.27
    POSITIVE LOGITS
    寕
    1.64
     dégustation
    1.55
    carnated
    1.48
    Tempat
    1.48
    Gründe
    1.48
     Nadie
    1.47
    ⚋
    1.47
    草莓
    1.46
    Ако
    1.45
    鏤
    1.45
    Activations Density 0.003%

    No Known Activations