© 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. 15333
    Prev
    Next
    INDEX
    Explanations

    code errors and exceptions

    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
    翃
    -2.88
    窳
    -2.63
    en
    -2.55
    饜
    -2.45
    
    -2.41
    msford
    -2.38
    淩
    -2.34
    ایق
    -2.34
     dubious
    -2.33
    л
    -2.31
    POSITIVE LOGITS
    0
    3.86
    1
    3.81
    乆
    2.97
    ↵
    2.63
    鈇
    2.59
    8
    2.38
    4
    2.34
    喼
    2.33
     塗
    2.31
    some
    2.28
    Activations Density 0.009%

    No Known Activations