© 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. 99892
    Prev
    Next
    INDEX
    Explanations

    delayed effects or outcomes

    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
     The
    -2.36
    ⢊
    -2.23
    皤
    -2.23
    鶻
    -2.14
    的发展
    -2.08
    嵙
    -2.08
     แต่
    -2.06
    
    -1.96
    里有
    -1.92
     современных
    -1.88
    POSITIVE LOGITS
    what
    2.95
    will
    2.86
    殽
    2.56
    此前
    2.45
    
    2.38
    ة
    2.33
    The
    2.28
    Why
    2.19
    we
    2.19
    。”
    2.17
    Activations Density 0.008%

    No Known Activations