© 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. 72271
    Prev
    Next
    INDEX
    Explanations

    events happening after

    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
     mindestens
    -1.82
    ICOLON
    -1.77
    𖣔
    -1.75
     eerste
    -1.69
    kebox
    -1.59
     reír
    -1.57
    気持ちを
    -1.56
     organisiert
    -1.56
     otras
    -1.55
     outras
    -1.53
    POSITIVE LOGITS
    焢
    1.76
    这
    1.63
     maroc
    1.58
     entrées
    1.56
    槼
    1.51
     anadolu
    1.50
     نیز
    1.49
    豋
    1.49
     素描
    1.49
     ingredi
    1.48
    Activations Density 0.018%

    No Known Activations