© 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. 34-GEMMASCOPE-RES-131K
    7. 47136
    Prev
    Next
    INDEX
    Explanations

    Objective-C ivar declarations

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     aŭ
    -0.81
     Batch
    -0.79
     Ship
    -0.77
     беремен
    -0.74
     Kreuz
    -0.73
     tabi
    -0.73
    ceptives
    -0.71
     Duc
    -0.71
     Vergleich
    -0.70
     câncer
    -0.68
    POSITIVE LOGITS
     desem
    0.82
     Elasticsearch
    0.81
     foxes
    0.80
     though
    0.77
    اون
    0.77
    cijos
    0.77
     elbows
    0.77
     overjoyed
    0.77
    idential
    0.76
     グラン
    0.76
    Activations Density 0.038%

    No Known Activations