© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239585
    Prev
    Next
    INDEX
    Explanations

    insurance on your dog

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    0.50
     matter
    0.50
    ait
    0.48
     in
    0.46
     Results
    0.46
    \\
    0.45
     मध्ये
    0.45
     n
    0.44
     repl
    0.44
    enteri
    0.44
    POSITIVE LOGITS
    ண்ணாம
    0.55
     wysoko
    0.53
    mydb
    0.52
     मुताब
    0.52
    uniqueItems
    0.52
    incomplete
    0.51
     духов
    0.50
     deewana
    0.49
    webElement
    0.49
     Priyanka
    0.49
    Activations Density 0.000%

    No Known Activations