© 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. 15446
    Prev
    Next
    INDEX
    Explanations

    multilingual terms

    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
     exquisitely
    -1.74
     from
    -1.72
     undeniably
    -1.68
     substantially
    -1.66
     Surprisingly
    -1.63
     sizeable
    -1.62
     tremendously
    -1.62
     burgeoning
    -1.61
     miliar
    -1.58
     continuously
    -1.55
    POSITIVE LOGITS
     utilisé
    1.77
     vê
    1.66
     pasan
    1.59
     blatant
    1.59
     hacen
    1.58
     บ
    1.58
    也得
    1.56
     charmant
    1.55
     same
    1.54
     mediocre
    1.54
    Activations Density 0.016%

    No Known Activations