© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75610
    Prev
    Next
    INDEX
    Explanations

    I you we verb

    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
    llte
    -1.83
    餍
    -1.83
    𓁹
    -1.83
     diren
    -1.80
    {
    -1.77
     квартире
    -1.76
     atencion
    -1.70
    
    -1.70
    ем
    -1.70
    嗵
    -1.70
    POSITIVE LOGITS
     to
    2.58
    那时
    2.28
    鹋
    2.19
     entspre
    2.02
    趼
    1.88
     größer
    1.86
     seminal
    1.85
     zusätz
    1.84
    整天
    1.84
    </h3>
    1.82
    Activations Density 0.020%

    No Known Activations