© 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. 22630
    Prev
    Next
    INDEX
    Explanations

    historical figures and writers

    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
    erende
    -1.32
    ;
    -1.30
    );
    -1.27
     oleh
    -1.25
     fMRI
    -1.22
    usschuss
    -1.19
    𝒓
    -1.18
    ERATION
    -1.17
     no
    -1.16
    ✰
    -1.16
    POSITIVE LOGITS
     vorgesch
    1.28
     offensichtlich
    1.27
    写的
    1.27
     tendrá
    1.23
    </strong>
    1.23
     microfibra
    1.22
     improvement
    1.21
     jederzeit
    1.19
     empfohlen
    1.19
     tendrán
    1.17
    Activations Density 0.048%

    No Known Activations