© 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. 98702
    Prev
    Next
    INDEX
    Explanations

    reach

    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
    Negative Logits
     なら
    -2.61
    </h3>
    -2.52
    </h1>
    -2.47
    enablog
    -2.31
    玬
    -2.30
    玊
    -2.22
    翃
    -2.22
    𓐍
    -2.17
    鱻
    -2.14
    鯓
    -2.05
    POSITIVE LOGITS
    ꠥ
    2.36
    這些
    2.30
    s
    2.22
    
    2.20
    </td>
    2.14
    因为他
    2.14
    Ruju
    2.13
    ings
    2.11
    尤其是
    2.08
     They
    2.06
    Activations Density 0.009%

    No Known Activations