© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57333
    Prev
    Next
    INDEX
    Explanations

    arabic script and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    দীর্ঘ
    0.42
    Because
    0.39
    減
    0.39
    ﻖ
    0.38
     or
    0.37
    Dr
    0.37
    {
    0.37
    financing
    0.37
     অন্যতম
    0.37
    ADD
    0.37
    POSITIVE LOGITS
    itando
    0.49
    iciado
    0.48
    eritud
    0.46
    ཌ
    0.45
    яў
    0.45
     Правда
    0.44
    ный
    0.43
     Ú
    0.43
    र्टी
    0.43
    न्तु
    0.42
    Activations Density 0.019%

    No Known Activations