© 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. 15498
    Prev
    Next
    INDEX
    Explanations

    suggesting a better option

    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
    Not in Any Lists

    No Comments

    Negative Logits
    R
    -1.52
     такими
    -1.48
    </b>
    -1.47
    我没
    -1.46
    理由は
    -1.46
    C
    -1.45
     Tatsache
    -1.45
    ၟ
    -1.45
     способом
    -1.45
     на
    -1.44
    POSITIVE LOGITS
     uſed
    1.68
     ſta
    1.63
    »?
    1.54
     自己
    1.49
    LANDS
    1.48
     зробити
    1.48
     内衣
    1.45
    however
    1.45
    somebody
    1.45
     ſte
    1.45
    Activations Density 0.021%

    No Known Activations