© 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. 48852
    Prev
    Next
    INDEX
    Explanations

    system implementation // Distributed Cloud Training 2 Comments

    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
    红包
    -0.73
    eof
    -0.73
     licensing
    -0.72
     matéria
    -0.71
     belles
    -0.71
    space
    -0.70
     ২
    -0.70
    amata
    -0.70
     oczy
    -0.69
    pId
    -0.69
    POSITIVE LOGITS
     hybrid
    0.92
    Hybrid
    0.83
     Hybrid
    0.82
    Jump
    0.80
     Jump
    0.79
    ometrica
    0.79
     Zeno
    0.78
     jump
    0.76
    hybrid
    0.73
     mode
    0.73
    Activations Density 0.016%

    No Known Activations