© 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. 82301
    Prev
    Next
    INDEX
    Explanations

    motorcycle brands and parts

    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
    บล
    -0.81
    ガリ
    -0.76
     throttle
    -0.74
    𝒔
    -0.73
     ül
    -0.73
     Blogs
    -0.72
     caterpillar
    -0.72
     بها
    -0.72
     Girlfriend
    -0.71
    NIT
    -0.71
    POSITIVE LOGITS
    uffle
    0.79
    sequently
    0.78
    Width
    0.75
    ън
    0.75
    ترة
    0.70
     企业
    0.70
    COAL
    0.69
    texture
    0.69
    ULATOR
    0.69
     Gorb
    0.68
    Activations Density 0.009%

    No Known Activations