© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38507
    Prev
    Next
    INDEX
    Explanations

    Javier and epoxy

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

    The neuron fires on the first content word of a sentence—that is, capitalized tokens occurring at sentence start.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ܇
    -2.44
    Ꮸ
    -2.42
     donker
    -2.38
     You
    -2.34
    睺
    -2.31
     corrupción
    -2.28
     rufen
    -2.27
    这本书
    -2.22
     flourishing
    -2.20
    食物
    -2.19
    POSITIVE LOGITS
    {
    3.20
    }$
    2.38
    )，
    2.34
    圌
    2.27
    </strong>
    2.27
     xxvi
    2.16
    s
    2.16
    .
    2.14
    k
    2.09
    ar
    2.08
    Activations Density 0.003%

    No Known Activations