© 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. 93052
    Prev
    Next
    INDEX
    Explanations

    dates, names, and foreign words

    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
    或是
    -0.77
     or
    -0.76
    ;
    -0.73
     Mannschaft
    -0.73
     Wern
    -0.73
    Clarke
    -0.72
     silently
    -0.71
     arguably
    -0.71
    Mrs
    -0.71
    Nov
    -0.71
    POSITIVE LOGITS
    footnotes
    0.94
    COMO
    0.84
    FICHA
    0.83
    Зміст
    0.82
    িল
    0.82
     aware
    0.79
     ASM
    0.79
    Внимание
    0.79
    鸪
    0.78
    Выбор
    0.78
    Activations Density 0.005%

    No Known Activations