© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108096
    Prev
    Next
    INDEX
    Explanations

    geeks or geckos

    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
    Not in Any Lists

    No Comments

    Negative Logits
    千代
    -0.76
     alti
    -0.76
     orig
    -0.75
     repaired
    -0.75
    ticals
    -0.73
     nóng
    -0.72
    شرين
    -0.71
    asm
    -0.71
    Einf
    -0.71
     geogra
    -0.70
    POSITIVE LOGITS
     Maori
    0.77
     खरीद
    0.75
    Laugh
    0.75
     subsections
    0.74
    lible
    0.73
    骼
    0.70
     Primal
    0.69
    نان
    0.68
    まれ
    0.68
    "]
    0.67
    Activations Density 0.015%

    No Known Activations