© 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. 93276
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and numbers

    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
     possibilités
    -1.06
     kjem
    -0.95
     capacités
    -0.95
     funzioni
    -0.95
     inconvénients
    -0.91
    킁
    -0.91
    已经
    -0.90
     ieg
    -0.90
     barres
    -0.90
     ateş
    -0.89
    POSITIVE LOGITS
     three
    1.14
     four
    1.14
     two
    1.09
     ends
    1.05
     combines
    1.03
     a
    1.02
    月亮
    1.00
     Three
    0.97
     Lead
    0.97
     clear
    0.96
    Activations Density 0.067%

    No Known Activations