© 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. 27597
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and units

    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
    Despite
    -2.23
    虽然
    -2.22
    There
    -2.14
    Having
    -2.14
    While
    -2.13
    当然
    -2.11
    Perhaps
    -2.08
    在
    -2.08
    ！！！！
    -2.05
     There
    -2.03
    POSITIVE LOGITS
    {
    2.73
     to
    2.47
     crucial
    2.34
    .
    2.34
     nowy
    2.30
     ina
    2.23
    
    2.22
     amd
    2.19
     deft
    2.17
     renowned
    2.16
    Activations Density 0.001%

    No Known Activations