© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7671
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_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
    د
    3.14
    ه
    2.66
    ح
    2.63
    i
    2.61
    ل
    2.27
    ي
    2.20
    ب
    2.16
    ið
    2.03
    ל
    2.02
    ور
    2.00
    POSITIVE LOGITS
    {~
    1.99
    lığ
    1.84
     Außerdem
    1.81
     favoring
    1.81
    ﻴ
    1.79
     lahan
    1.73
    arası
    1.71
     inneh
    1.68
    infile
    1.67
     außen
    1.67
    Activations Density 0.226%

    No Known Activations