© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30970
    Prev
    Next
    INDEX
    Explanations

    legal licensing phrases

    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
    igos
    -0.86
     иллюстрация
    -0.76
    ających
    -0.71
    iermark
    -0.69
    Бер
    -0.69
     obiek
    -0.68
    ấn
    -0.68
    🫥
    -0.67
    reide
    -0.67
    資料
    -0.67
    POSITIVE LOGITS
     Conclusion
    0.74
     tel
    0.73
    Mystic
    0.72
    dz
    0.71
     учре
    0.71
    illet
    0.70
     ο
    0.70
     Minder
    0.69
    Float
    0.68
    Controllers
    0.68
    Activations Density 0.052%

    No Known Activations