© 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. 65409
    Prev
    Next
    INDEX
    Explanations

    prepositions, determiners, suffixes

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

    honoris causa, iterations, frequently

    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
    зву
    0.57
    Ｂ
    0.57
    Щ
    0.55
     Бон
    0.54
    DATUM
    0.54
    PHIA
    0.53
     বাঙ্গালী
    0.52
    เริ่ม
    0.52
     incapacitated
    0.52
    Б
    0.52
    POSITIVE LOGITS
    ize
    0.52
    rr
    0.52
    liste
    0.48
    ers
    0.48
    nt
    0.48
    ert
    0.48
    list
    0.47
    pres
    0.47
    oni
    0.47
    ships
    0.46
    Activations Density 0.000%

    No Known Activations