© 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. 10616
    Prev
    Next
    INDEX
    Explanations

    been followed by verbs

    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
    ने
    1.92
    ри
    1.90
    ня
    1.88
    ना
    1.77
     ina
    1.73
    нях
    1.70
     eben
    1.63
    d
    1.63
    san
    1.63
    ре
    1.59
    POSITIVE LOGITS
    ։
    2.08
    ния
    2.05
    ി
    1.95
    ้อง
    1.92
    รัก
    1.86
    jų
    1.84
    ر
    1.82
    ,【
    1.80
    ę
    1.77
    ມ
    1.75
    Activations Density 0.025%

    No Known Activations