© 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. 62501
    Prev
    Next
    INDEX
    Explanations

    two way communication and crossover

    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
    Én
    -0.90
     resurre
    -0.85
    Fornecedor
    -0.85
     Downvote
    -0.84
     riduzione
    -0.83
     Quod
    -0.82
    Existe
    -0.81
    Опис
    -0.78
     volverá
    -0.78
    级的
    -0.77
    POSITIVE LOGITS
     streets
    1.10
     traffic
    1.07
    послед
    0.98
     ANOVA
    0.97
     accountability
    0.94
     valve
    0.93
    streets
    0.93
    street
    0.90
     ticket
    0.90
     улицы
    0.90
    Activations Density 0.017%

    No Known Activations