© 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. 118499
    Prev
    Next
    INDEX
    Explanations

    software licenses and specific software names

    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
    wania
    -0.81
     Algo
    -0.81
    devo
    -0.77
     Wonders
    -0.76
    atakan
    -0.71
    ้า
    -0.71
     Pliny
    -0.69
    每個
    -0.69
     télécharge
    -0.68
     Kích
    -0.68
    POSITIVE LOGITS
    tellbar
    0.79
    زة
    0.79
    橙
    0.77
    Postal
    0.76
    iſ
    0.76
    Limitation
    0.73
    sodium
    0.73
     sodium
    0.72
    Mileage
    0.71
    +[
    0.71
    Activations Density 0.002%

    No Known Activations