© 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-262K
    7. 37523
    Prev
    Next
    INDEX
    Explanations

    debit and prepaid cards

    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_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
     estaven
    1.52
     而且
    1.38
    们
    1.30
    ans
    1.27
     hebben
    1.25
     ensued
    1.25
    iquity
    1.23
    的时间
    1.23
    enna
    1.23
    ala
    1.22
    POSITIVE LOGITS
    ها
    1.17
    ЕВ
    1.17
     maladies
    1.13
    이면
    1.12
    ^{+}\
    1.09
    ேய
    1.09
     fronts
    1.09
    АР
    1.08
     mils
    1.08
    น้อง
    1.06
    Activations Density 0.000%

    No Known Activations