© 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. 67594
    Prev
    Next
    INDEX
    Explanations

    numbers and hyphens

    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
     the
    -2.14
    </td>
    -1.97
     decides
    -1.91
    チーフ
    -1.91
     ‌
    -1.89
     letz
    -1.86
     необходимо
    -1.85
    こども
    -1.84
    フォト
    -1.82
    チェンジ
    -1.80
    POSITIVE LOGITS
     醬
    2.45
    ⽌
    2.45
    脔
    2.41
    鬭
    2.25
     hunne
    2.19
    viele
    2.19
    歺
    2.17
     การ์ตูน
    2.16
    毉
    2.16
     какво
    2.09
    Activations Density 0.117%

    No Known Activations