© 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. 10601
    Prev
    Next
    INDEX
    Explanations

    liability protection

    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
    無論
    2.20
    이었다
    2.14
    í
    2.11
    एस
    2.06
     thermique
    1.90
    ის
    1.86
    ならば
    1.84
     đích
    1.83
    Οι
    1.81
    ılarak
    1.81
    POSITIVE LOGITS
    ن
    2.70
    ت
    2.48
    ed
    2.33
    ли
    2.23
    es
    2.11
    ens
    2.08
    a
    2.08
    н
    1.98
    n
    1.96
    aer
    1.95
    Activations Density 0.050%

    No Known Activations