© 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. 190191
    Prev
    Next
    INDEX
    Explanations

    application process

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

    thread, codename, file, faction, charts, deed

    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
     लर्न
    0.42
     ዘዴ
    0.42
     ዓይነት
    0.41
    ^^^^
    0.41
     wrangler
    0.40
     televisions
    0.39
    ogee
    0.39
     હશે
    0.39
     dermatology
    0.39
    agnar
    0.38
    POSITIVE LOGITS
    찢
    0.50
    אס
    0.49
    מש
    0.48
    ัป
    0.48
    highlight
    0.47
    يس
    0.46
    بو
    0.46
    бло
    0.46
    وء
    0.45
     evocative
    0.45
    Activations Density 0.000%

    No Known Activations