© 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. 34-GEMMASCOPE-RES-131K
    7. 117137
    Prev
    Next
    INDEX
    Explanations

    may, possibility, or dates

    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
     Bisa
    -0.91
    ıyoruz
    -0.90
     можна
    -0.90
    ꯤ
    -0.85
     можно
    -0.85
    можно
    -0.81
     Jpn
    -0.80
     Можно
    -0.78
    Можно
    -0.78
    testCase
    -0.77
    POSITIVE LOGITS
     may
    5.84
     May
    4.28
    May
    4.06
    may
    3.94
     MAY
    2.84
    MAY
    2.48
     может
    2.25
     мая
    1.94
     могут
    1.88
     ممکن
    1.86
    Activations Density 0.046%

    No Known Activations