© 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. 15708
    Prev
    Next
    INDEX
    Explanations

    categories and miscellaneous items

    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
    link
    0.59
    (
    0.57
    t
    0.55
    l
    0.54
    sp
    0.53
    n
    0.53
    T
    0.53
    m
    0.52
     implications
    0.52
    r
    0.51
    POSITIVE LOGITS
     Miscellaneous
    1.10
     Misc
    1.10
     miscellaneous
    1.09
     &
    0.97
     Kategorie
    0.96
    Miscellaneous
    0.96
     Category
    0.91
     catégorie
    0.91
    Misc
    0.90
     categorie
    0.89
    Activations Density 0.478%

    No Known Activations