© 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. 14705
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code

    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
    雳
    -2.58
    ৄ
    -2.38
     怎么
    -2.27
    慤
    -2.19
    
    -2.19
    }-\
    -2.17
     сили
    -2.16
    𝄆
    -2.11
    するので
    -2.09
    ｿ
    -2.09
    POSITIVE LOGITS
     
    3.02
    er
    2.86
    an
    2.44
     nowej
    2.34
     تقدم
    2.34
    most
    2.33
    两人的
    2.25
     verschillende
    2.23
    部分は
    2.23
    having
    2.22
    Activations Density 0.002%

    No Known Activations