© 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. 10-GEMMASCOPE-RES-131K
    7. 58635
    Prev
    Next
    INDEX
    Explanations

    specific acronyms and product names

    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_10/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
     and
    -2.16
     because
    -2.05
    There
    -2.03
     there
    -2.02
     That
    -1.99
     with
    -1.99
     after
    -1.98
    after
    -1.95
     during
    -1.90
    there
    -1.89
    POSITIVE LOGITS
     famed
    1.88
    苙
    1.80
     magnific
    1.77
     Quando
    1.71
     horrid
    1.69
    䊳
    1.64
     revered
    1.58
     현재
    1.55
    kinda
    1.55
     soooo
    1.55
    Activations Density 0.314%

    No Known Activations