© 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. 109267
    Prev
    Next
    INDEX
    Explanations

    search engine marketing

    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
    ülü
    -0.79
    taya
    -0.77
     учи
    -0.74
    家庭
    -0.74
    fektions
    -0.73
     anota
    -0.72
    gelegen
    -0.71
    物品
    -0.71
    пут
    -0.70
    Fcn
    -0.69
    POSITIVE LOGITS
     SEO
    2.84
    SEO
    2.44
     seo
    2.14
    seo
    2.00
     PPC
    1.78
     SEM
    1.69
    Seo
    1.66
     Seo
    1.58
    SEM
    1.53
    PPC
    1.49
    Activations Density 0.093%

    No Known Activations