© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 332
    Prev
    Next
    INDEX
    Explanations

    mathematical notation subscripts

    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
     ones
    -0.85
    मान
    -0.81
    下的
    -0.79
    из
    -0.78
    ȯ
    -0.77
     vaj
    -0.77
     استفاده
    -0.77
    zeta
    -0.76
    ErrUnexpected
    -0.75
    beta
    -0.75
    POSITIVE LOGITS
    </em>
    1.12
     että
    1.05
    年は
    1.03
     päivä
    1.00
     胶
    0.96
     діяльності
    0.94
     määrä
    0.92
     kautta
    0.90
    rå
    0.90
     muttered
    0.90
    Activations Density 0.012%

    No Known Activations