© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1206
    Prev
    Next
    INDEX
    Explanations

    code blocks and structured lists

    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
     downloader
    0.56
     npm
    0.55
     editor
    0.54
    ydia
    0.52
    ipeline
    0.52
     DECL
    0.52
     Editor
    0.52
    /__
    0.52
    タリア
    0.52
     Parser
    0.52
    POSITIVE LOGITS
    enumerate
    1.09
     enumerate
    1.00
     enumerated
    0.76
    tabular
    0.66
    itemize
    0.63
    eqnarray
    0.62
     enumer
    0.61
    framed
    0.58
    CJK
    0.57
    sorted
    0.57
    Activations Density 0.166%

    No Known Activations