© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128184
    Prev
    Next
    INDEX
    Explanations

    words ending in ise

    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
    淠
    -3.22
    
    -2.95
     
    -2.69
    其妙
    -2.58
    亊
    -2.50
     Our
    -2.44
     grijs
    -2.42
    宬
    -2.41
    蟶
    -2.38
    :”
    -2.36
    POSITIVE LOGITS
    e
    2.44
    {
    2.41
     `
    2.34
    😂
    2.14
    ISE
    2.13
     grupper
    2.11
    اً
    2.06
    䊐
    2.06
     försö
    2.05
     stål
    2.05
    Activations Density 0.014%

    No Known Activations