© 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. 22-GEMMASCOPE-RES-131K
    7. 98319
    Prev
    Next
    INDEX
    Explanations

    film writingmembers and dropdownsexercise and nomedical angioplasty

    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_22/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
     adelantado
    -0.97
     nuestra
    -0.96
    ərb
    -0.90
     adelant
    -0.88
     soo
    -0.87
    不应该
    -0.86
    アの
    -0.86
    Они
    -0.84
    游戏的
    -0.84
    に関
    -0.84
    POSITIVE LOGITS
     habitudes
    0.85
     few
    0.84
     latter
    0.82
     милли
    0.80
    SHOW
    0.80
     フィギュア
    0.79
    Simulator
    0.79
    ①
    0.78
    ();
    0.78
     Schwert
    0.78
    Activations Density 0.098%

    No Known Activations