© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 11851
    Prev
    Next
    INDEX
    Explanations

    j followed by punctuation or abbreviations

    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
     завода
    2.00
     jasa
    1.98
     loafers
    1.98
    اب
    1.96
    ний
    1.94
    ropri
    1.86
    -\
    1.84
    )}}{
    1.84
    ্যার
    1.82
    ется
    1.81
    POSITIVE LOGITS
     Darüber
    2.27
    骜
    2.16
    驁
    2.13
    િ
    2.08
     Printer
    2.06
    ל
    2.06
    みると
    2.03
     keterampilan
    2.03
    ش
    2.03
     Međutim
    2.00
    Activations Density 0.263%

    No Known Activations