© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6853
    Prev
    Next
    INDEX
    Explanations

    chemical functional groups and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    ෲ
    0.37
     GOODS
    0.35
     indiqu
    0.34
     wirtschaft
    0.33
     literatura
    0.33
     শাজ
    0.33
     ekonomik
    0.33
     ekonom
    0.32
     çeşitli
    0.32
    िरिक्स
    0.32
    POSITIVE LOGITS
    -
    0.47
    ths
    0.31
    фи
    0.29
    ск
    0.29
    -"
    0.28
    -#
    0.28
    rate
    0.28
     romanos
    0.28
    create
    0.28
    cel
    0.28
    Activations Density 0.006%

    No Known Activations