© 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. 10490
    Prev
    Next
    INDEX
    Explanations

    explains name origin or reason

    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
    ل
    2.17
    र
    1.86
    у
    1.85
    länd
    1.77
    ar
    1.71
    م
    1.69
    но
    1.66
    ам
    1.62
    ної
    1.61
     nutshell
    1.60
    POSITIVE LOGITS
     aclar
    1.55
     מאוד
    1.55
     estudi
    1.54
    rition
    1.52
     cerr
    1.49
    عات
    1.47
     দায়ী
    1.47
    um
    1.45
    ظر
    1.45
    ಗಾರ
    1.45
    Activations Density 0.011%

    No Known Activations