© 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. 72095
    Prev
    Next
    INDEX
    Explanations

    legal documents and code contexts

    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
     mindig
    -1.41
     =
    -1.38
     booming
    -1.30
    ность
    -1.30
     trebui
    -1.28
     abrasive
    -1.27
    laması
    -1.26
     établi
    -1.23
     ALWAYS
    -1.22
    兩
    -1.21
    POSITIVE LOGITS
    渽
    1.87
    龱
    1.76
    ༷
    1.70
    fillment
    1.69
     that
    1.64
    eliner
    1.63
    ;-
    1.61
    IR
    1.59
    ⩕
    1.59
    tivities
    1.52
    Activations Density 0.001%

    No Known Activations