© 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. 10230
    Prev
    Next
    INDEX
    Explanations

    a followed by word

    np_acts-logits-general · gemini-2.5-flash-lite

    cybersecurity, mathematical, Earth

    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
    ika
    0.50
    sorting
    0.48
    涤
    0.48
    kay
    0.47
    Collections
    0.45
    jak
    0.45
    jiang
    0.44
    introspection
    0.44
    은
    0.44
    heap
    0.44
    POSITIVE LOGITS
     substitu
    0.51
     midrange
    0.49
    สังคม
    0.49
     Hartree
    0.48
     conclure
    0.48
     excused
    0.47
     volante
    0.46
     militare
    0.46
     paroles
    0.46
     cantante
    0.46
    Activations Density 0.000%

    No Known Activations