© 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. 6370
    Prev
    Next
    INDEX
    Explanations

    EPA

    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
    Negative Logits
     ومن
    1.76
    withtag
    1.76
    ম
    1.69
    ó
    1.62
     נו
    1.58
    <0xB4>
    1.55
    ோ
    1.55
    ร่วม
    1.52
    たと
    1.45
    ü
    1.41
    POSITIVE LOGITS
    cary
    2.05
    cers
    1.98
    kken
    1.94
    cem
    1.70
    ں
    1.69
    al
    1.68
    ially
    1.66
    c
    1.66
    ్
    1.65
    inės
    1.64
    Activations Density 0.001%

    No Known Activations