© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9453
    Prev
    Next
    INDEX
    Explanations

    academic citation links

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     bothering
    0.61
     Widers
    0.57
     esimerkiksi
    0.53
     Others
    0.51
     क्षेत्र
    0.50
     beispielsweise
    0.50
     dungeon
    0.50
     Bolts
    0.50
     ██
    0.50
     sued
    0.50
    POSITIVE LOGITS
    th
    0.57
    లుగా
    0.55
     rata
    0.54
    配合
    0.53
    传统的
    0.51
    oração
    0.50
     sering
    0.50
    ณ
    0.49
    วัฒ
    0.48
    融入
    0.48
    Activations Density 0.001%

    No Known Activations