© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98960
    Prev
    Next
    INDEX
    Explanations

    websites and online content

    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
     اینستاگرام
    -0.90
     peuple
    -0.88
    スタジオ
    -0.80
     tales
    -0.79
    getHeaders
    -0.79
     Tiktok
    -0.77
    inars
    -0.77
     romances
    -0.77
     material
    -0.75
    ARON
    -0.75
    POSITIVE LOGITS
     sites
    1.63
     websites
    1.38
    sites
    1.21
     aggreg
    1.14
     specialized
    0.94
     news
    0.92
    hébergement
    0.91
     aggregation
    0.91
     reputable
    0.89
     popular
    0.87
    Activations Density 0.104%

    No Known Activations