© 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. 3372
    Prev
    Next
    INDEX
    Explanations

    quotation marks or enclosing symbols

    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
     nbsp
    0.59
     [...]
    0.56
     \...
    0.56
    ‎
    0.56
     [...
    0.55
     博文
    0.55
    」，
    0.54
    [,
    0.54
    ायती
    0.53
    পুত্র
    0.52
    POSITIVE LOGITS
     "
    3.58
     “
    3.33
     ‘
    3.11
     '
    3.02
     「
    2.73
     «
    2.63
    「
    2.45
     „
    2.34
     cosidd
    2.34
    ｢
    2.34
    Activations Density 1.574%

    No Known Activations