© 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. 83838
    Prev
    Next
    INDEX
    Explanations

    honestly, literally, seriously

    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
     of
    -1.94
    </h5>
    -1.54
    他
    -1.39
    。”
    -1.38
    ").
    -1.37
    蒾
    -1.37
    }\
    -1.36
    )}\
    -1.35
     })
    -1.34
     ´
    -1.33
    POSITIVE LOGITS
     only
    1.41
     兩
    1.41
     ayudó
    1.38
    pisah
    1.36
    <
    1.31
     acknowledges
    1.29
     autobús
    1.29
     trasero
    1.29
    یین
    1.27
     sends
    1.27
    Activations Density 0.013%

    No Known Activations