© 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. 22-GEMMASCOPE-RES-131K
    7. 71432
    Prev
    Next
    INDEX
    Explanations

    html elements and tags

    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_22/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
    来週
    -1.33
     kupić
    -1.17
     pozw
    -1.16
    ススメ
    -1.16
     dopiero
    -1.16
     Each
    -1.15
     Of
    -1.14
     the
    -1.14
    ほうがいい
    -1.13
    ほら
    -1.13
    POSITIVE LOGITS
    <bos>
    1.57
    <0xA3>
    1.52
    や
    1.29
    もあって
    1.24
    では
    1.23
     heridos
    1.16
    🩻
    1.16
    などは
    1.14
    álisis
    1.13
    商品説明
    1.11
    Activations Density 0.001%

    No Known Activations