© 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. 22-GEMMASCOPE-RES-131K
    7. 70647
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and translations

    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
    :
    -0.88
    最後に
    -0.87
     another
    -0.85
    全都
    -0.82
     عبدالله
    -0.81
    それを
    -0.80
     others
    -0.79
     suele
    -0.79
    losse
    -0.78
    uvre
    -0.78
    POSITIVE LOGITS
     också
    1.06
     bambou
    1.05
     også
    1.00
    着头
    0.99
    НИ
    0.97
    🍀
    0.94
     أيضًا
    0.91
     also
    0.91
     یعنی
    0.91
     גם
    0.90
    Activations Density 0.024%

    No Known Activations