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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89796
    Prev
    Next
    INDEX
    Explanations

    LeftNav, routes, code

    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
     kond
    -0.77
    ਵ
    -0.75
    čit
    -0.72
     ห
    -0.69
    我希望
    -0.69
     успо
    -0.67
     Hütte
    -0.67
     coloring
    -0.67
     much
    -0.67
     日
    -0.67
    POSITIVE LOGITS
    hauses
    0.84
    платье
    0.79
    phones
    0.79
    controlled
    0.77
    нер
    0.76
    めていた
    0.75
     rempli
    0.75
    hai
    0.74
     demos
    0.73
    see
    0.73
    Activations Density 0.007%

    No Known Activations