© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74752
    Prev
    Next
    INDEX
    Explanations

    sparked, initiating actions or reactions

    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
    {
    -2.25
    憮
    -2.02
     یا
    -1.98
     و
    -1.87
    </h3>
    -1.81
     belga
    -1.76
    躥
    -1.75
     }}$.
    -1.74
    .';
    -1.68
     atau
    -1.66
    POSITIVE LOGITS
    
    2.08
    他的
    2.02
    此事
    1.98
    苼
    1.88
    呷
    1.85
     alberga
    1.80
    upb
    1.74
    tA
    1.74
    潆
    1.74
    并没有
    1.72
    Activations Density 0.015%

    No Known Activations