© 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. 14301
    Prev
    Next
    INDEX
    Explanations

    roast food and coffee

    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
    菹
    -2.47
    競馬
    -2.36
    ise
    -2.31
    Ꝑ
    -2.25
    嘥
    -2.23
     花卉
    -2.22
    ay
    -2.19
    嗵
    -2.17
    
    -2.17
    oo
    -2.16
    POSITIVE LOGITS
    ↵
    2.58
    龊
    2.48
     streamlining
    2.42
     exceptional
    2.41
     ferner
    2.39
    眼光
    2.39
     $
    2.38
     renowned
    2.34
    -
    2.30
     unrivalled
    2.25
    Activations Density 0.002%

    No Known Activations