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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 13456
    Prev
    Next
    INDEX
    Explanations

    step-by-step process

    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
    ными
    1.38
    :
    1.29
    zeit
    1.28
    י
    1.27
    udrait
    1.26
    _{-}^{
    1.26
     gegründet
    1.23
     seja
    1.22
     выбира
    1.22
     بطور
    1.21
    POSITIVE LOGITS
    urbance
    1.33
    <0xA9>
    1.24
    HCM
    1.23
    ৬
    1.21
     partant
    1.13
     filer
    1.12
    ە
    1.11
     aides
    1.10
    エンス
    1.09
    häng
    1.08
    Activations Density 0.211%

    No Known Activations