© 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-262K
    7. 40264
    Prev
    Next
    INDEX
    Explanations

    magnets attract or repel

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ج
    1.66
    ف
    1.48
    י
    1.48
    ल
    1.42
    اب
    1.41
    ном
    1.36
    غ
    1.34
    ли
    1.34
    ze
    1.29
     ў
    1.27
    POSITIVE LOGITS
    <0x80>
    1.73
    们
    1.67
    ంచెం
    1.48
    说
    1.34
    وں
    1.31
    sons
    1.30
    larına
    1.26
    ların
    1.25
    CA
    1.24
    akit
    1.23
    Activations Density 0.004%

    No Known Activations