© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15399
    Prev
    Next
    INDEX
    Explanations

    section separators or structured text elements

    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_31_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
     एवं
    0.27
     সমস্ত
    0.25
    ேய
    0.23
    áh
    0.22
     sows
    0.22
     نہایت
    0.22
     slats
    0.22
    ｅ
    0.21
    엷
    0.21
     presque
    0.21
    POSITIVE LOGITS
    JsonResponse
    0.25
     কারও
    0.24
    ˨
    0.23
    Ⲱ
    0.22
    公益
    0.22
     কখনও
    0.22
     néanmoins
    0.21
     #{@
    0.20
    ⟤
    0.20
     мисте
    0.20
    Activations Density 2.494%

    No Known Activations