© 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. 22-GEMMASCOPE-RES-131K
    7. 34854
    Prev
    Next
    INDEX
    Explanations

    uncertainty or lack of knowledge

    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_22/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
     to
    -1.30
     漫画
    -1.15
    好不容易
    -1.13
    ướng
    -1.13
     you
    -1.09
     farklı
    -1.07
    omenti
    -1.07
     how
    -1.05
     nasıl
    -1.02
     Wasn
    -1.02
    POSITIVE LOGITS
    "
    1.05
     rojos
    0.94
     gutem
    0.94
    Everyday
    0.93
     temprano
    0.92
    Feel
    0.91
     Substanz
    0.91
     sekali
    0.90
     сър
    0.89
    那么多
    0.89
    Activations Density 0.012%

    No Known Activations