© 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. 68586
    Prev
    Next
    INDEX
    Explanations

    from the official website

    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
    ！”
    -1.94
    }
    -1.60
    "]
    -1.50
     $
    -1.48
     decía
    -1.47
    ２
    -1.47
    0
    -1.46
     kvě
    -1.44
    ！
    -1.43
    。。。
    -1.41
    POSITIVE LOGITS
     various
    1.63
     few
    1.62
     including
    1.49
     여성
    1.48
    擽
    1.44
     BIBLIO
    1.43
     VARIOUS
    1.43
    什么的
    1.41
     夜景
    1.41
    你来
    1.41
    Activations Density 0.047%

    No Known Activations