© 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. 79867
    Prev
    Next
    INDEX
    Explanations

    section headers and tutor information

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

    The neuron consistently lights up on structural outline elements—things like section headings, menu or table‐of‐contents links, and list‐item markers.

    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
    相変わらず
    -1.08
    HUS
    -0.99
     特徴
    -0.94
     Karakter
    -0.94
     Polka
    -0.94
     boty
    -0.94
     簡単
    -0.93
     intersper
    -0.93
     вікі
    -0.92
     Stefanie
    -0.91
    POSITIVE LOGITS
    Lastly
    1.31
     lastly
    1.27
     Lastly
    1.24
     and
    1.19
     Finally
    1.15
     finally
    1.11
     contact
    1.11
     it
    1.07
     legal
    1.01
     on
    1.00
    Activations Density 0.034%

    No Known Activations