© 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. 72260
    Prev
    Next
    INDEX
    Explanations

    accent and accents

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ⸫
    -2.81
    ی
    -2.70
    皷
    -2.53
     หรือ
    -2.53
    とおり
    -2.50
    ￪
    -2.45
    のよう
    -2.41
     інших
    -2.39
    嘬
    -2.38
    莇
    -2.36
    POSITIVE LOGITS
    ↵
    3.44
    the
    3.27
    and
    2.98
    </h2>
    2.95
    which
    2.84
    A
    2.84
    <em>
    2.70
    𖥦
    2.63
     и
    2.55
    </sup>
    2.38
    Activations Density 0.002%

    No Known Activations