© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128188
    Prev
    Next
    INDEX
    Explanations

    \item parameter descriptions

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

    The neuron detects documentation or markup section keywords (e.g. “title,” “item,” “footnote”) in the text.

    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
     of
    -2.66
     provocando
    -2.23
    詳しくは
    -2.13
     quinze
    -2.09
    
    -2.08
     участке
    -2.05
     แต่
    -2.02
    vantaged
    -2.02
     creando
    -1.91
    蚺
    -1.91
    POSITIVE LOGITS
    g
    2.42
    </strong>
    2.34
     Presumably
    2.20
     sebagai
    2.16
     verifique
    2.14
    This
    2.14
    ar
    2.14
    It
    2.11
    b
    2.09
    ：
    2.06
    Activations Density 0.001%

    No Known Activations