© 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. 6450
    Prev
    Next
    INDEX
    Explanations

    K, (

    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
    kende
    1.22
    k
    1.17
    kosten
    1.05
    kinder
    1.03
    kost
    1.02
     Nicht
    0.97
    сть
    0.95
    i
    0.91
    butter
    0.89
    ante
    0.88
    POSITIVE LOGITS
     decades
    1.05
     Cytol
    1.02
    Ⲥ
    0.94
     Menurut
    0.92
     pituitary
    0.89
    نا
    0.88
     Bahkan
    0.88
     présentes
    0.88
     heyday
    0.87
     landscaped
    0.85
    Activations Density 0.004%

    No Known Activations