© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6006
    Prev
    Next
    INDEX
    Explanations

    search example usage

    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
     (
    1.38
     has
    1.36
     this
    1.34
     This
    1.33
     +
    1.30
     from
    1.26
     [
    1.19
     &
    1.18
     -
    1.15
     is
    1.14
    POSITIVE LOGITS
     desempeño
    1.29
    businessman
    1.28
     empresario
    1.20
     empresarial
    1.16
    unternehmen
    1.16
    empio
    1.13
    itabbam
    1.13
    ARAJYA
    1.12
     кеңсеси
    1.10
    songwriter
    1.08
    Activations Density 0.221%

    No Known Activations