© 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. 6843
    Prev
    Next
    INDEX
    Explanations

    actor and writer names

    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
    ținut
    -1.59
     costuras
    -1.46
    ürtel
    -1.36
     beş
    -1.32
    rensen
    -1.30
    consulté
    -1.30
    ๗
    -1.29
    ৫
    -1.28
     initWithFrame
    -1.27
     şun
    -1.26
    POSITIVE LOGITS
    把我
    1.30
     aveva
    1.27
     tausend
    1.27
     Instantly
    1.23
    up
    1.16
    1
    1.09
     ähn
    1.09
     Verhält
    1.09
    つけて
    1.07
    ecte
    1.07
    Activations Density 0.138%

    No Known Activations