© 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. 77124
    Prev
    Next
    INDEX
    Explanations

    code comments and licenses

    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
    さも
    -0.78
    оны
    -0.77
     ZU
    -0.77
    ,-\
    -0.76
     marge
    -0.76
    CCIÓN
    -0.75
    ysty
    -0.75
    γραφία
    -0.74
     its
    -0.74
     diterima
    -0.73
    POSITIVE LOGITS
    置いて
    0.90
     out
    0.85
     Leiter
    0.79
    丢
    0.77
     نوز
    0.75
    break
    0.74
    forgot
    0.74
    continues
    0.71
     javax
    0.70
    宪
    0.70
    Activations Density 0.000%

    No Known Activations