© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102371
    Prev
    Next
    INDEX
    Explanations

    verbs and actions in multiple languages

    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
     görüntüleri
    -2.61
    ᠁
    -2.38
    u
    -2.36
    g
    -2.34
    谖
    -2.31
    d
    -2.30
     intoxicating
    -2.28
    r
    -2.27
    却又
    -2.23
    却不
    -2.23
    POSITIVE LOGITS
    );
    2.11
     gleichen
    2.09
    亠
    2.08
     男孩
    2.05
    UCIÓN
    2.03
     It
    2.00
    arão
    1.92
    			
    1.88
     séance
    1.87
    *}[
    1.86
    Activations Density 0.001%

    No Known Activations