© 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. 34-GEMMASCOPE-RES-131K
    7. 60657
    Prev
    Next
    INDEX
    Explanations

    lack or absence

    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_34/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
    ちょっとした
    -1.16
    QUIZ
    -1.00
    RESTAUR
    -0.96
     peculi
    -0.92
     coni
    -0.89
    PENG
    -0.89
    toarele
    -0.88
    维持
    -0.88
     wart
    -0.88
     aree
    -0.87
    POSITIVE LOGITS
     lacks
    1.50
     lacked
    1.09
     lack
    1.00
     doesn
    0.90
    كام
    0.85
     отсут
    0.84
    deficient
    0.84
     lacking
    0.83
    让
    0.82
    ไม่มี
    0.82
    Activations Density 0.000%

    No Known Activations