© 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. 23811
    Prev
    Next
    INDEX
    Explanations

    New York City buildings and events

    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
     trượt
    -0.76
    ADHD
    -0.72
    冻
    -0.70
     economic
    -0.68
    kik
    -0.68
    Crime
    -0.67
    вии
    -0.66
     Mike
    -0.66
     Rees
    -0.66
    idy
    -0.65
    POSITIVE LOGITS
    ינוך
    0.91
    箒
    0.79
    variance
    0.76
    lapsible
    0.73
    jde
    0.72
    Ҥ
    0.72
    RESET
    0.71
    மி
    0.71
     hydration
    0.71
    ilfe
    0.71
    Activations Density 0.008%

    No Known Activations