© 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. 22-GEMMASCOPE-RES-131K
    7. 26143
    Prev
    Next
    INDEX
    Explanations

    comfortable to use

    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_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
     सत्यापित
    -1.31
    odotus
    -1.30
     أيض
    -1.27
     المسؤول
    -1.27
    ־ה
    -1.23
     two
    -1.23
    に行ってきました
    -1.16
    嵯
    -1.16
    諫
    -1.16
     three
    -1.16
    POSITIVE LOGITS
     you
    1.75
     biedt
    1.35
     вам
    1.34
     your
    1.34
     features
    1.18
    доро
    1.16
    あなた
    1.14
    ‌‌
    1.09
    </th>
    1.09
    티
    1.09
    Activations Density 0.040%

    No Known Activations