© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30926
    Prev
    Next
    INDEX
    Explanations

    mathematical or code formulas

    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_65k_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
     Consultation
    0.48
    ื่ม
    0.44
    U
    0.44
    ки
    0.43
     Gardener
    0.43
    ’
    0.43
    Interview
    0.43
    1
    0.42
    Ch
    0.41
    2
    0.41
    POSITIVE LOGITS
     doar
    0.51
     scratched
    0.45
     debated
    0.44
     scrapped
    0.43
     ټ
    0.43
     incompre
    0.42
     delineated
    0.42
     spliced
    0.42
    ສ່ວນ
    0.42
     publicized
    0.42
    Activations Density 0.003%

    No Known Activations