© 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. 10-GEMMASCOPE-RES-131K
    7. 130537
    Prev
    Next
    INDEX
    Explanations

    code comments and requires

    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_10/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
    ⦊
    -2.80
    
    -2.66
     When
    -2.59
    我们是
    -2.53
    獁
    -2.50
    гії
    -2.50
    🫶
    -2.44
    ꜄
    -2.36
    錞
    -2.36
     главным
    -2.34
    POSITIVE LOGITS
    <
    3.22
     extremely
    2.92
     horrible
    2.88
     чёр
    2.88
     hugely
    2.83
     immense
    2.83
    [
    2.80
     breathtaking
    2.78
     Frequently
    2.77
     horrifying
    2.77
    Activations Density 0.000%

    No Known Activations