© 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. 10792
    Prev
    Next
    INDEX
    Explanations

    PAIR

    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
    I
    0.77
    F
    0.77
    様々な
    0.71
    D
    0.68
    edition
    0.67
    ਗ
    0.67
     това
    0.66
     enjeux
    0.66
    는다
    0.65
     Britann
    0.64
    POSITIVE LOGITS
    ු
    0.94
    ians
    0.86
    อร์
    0.82
     زيادة
    0.82
     starvation
    0.82
     peroxidase
    0.80
    apabb
    0.80
    ić
    0.80
     supergiants
    0.80
     antigüedad
    0.80
    Activations Density 0.001%

    No Known Activations