© 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. 32708
    Prev
    Next
    INDEX
    Explanations

    learning about and from

    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
    Kelebihan
    -1.02
    Selanjutnya
    -1.02
    gemeen
    -0.91
    kanie
    -0.87
    HttpGet
    -0.85
    Kesimpulan
    -0.83
     erhalten
    -0.82
    laven
    -0.82
    Samo
    -0.81
    vän
    -0.81
    POSITIVE LOGITS
     about
    1.68
     from
    1.60
     lessons
    1.28
     valuable
    1.25
     both
    1.05
     new
    1.04
     опыт
    0.98
    Lessons
    0.97
     useful
    0.96
     Lessons
    0.96
    Activations Density 0.015%

    No Known Activations