© 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. 51779
    Prev
    Next
    INDEX
    Explanations

    spend time or energy

    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
    емых
    0.61
    اب
    0.57
     an
    0.56
    ة
    0.55
    его
    0.54
     препарата
    0.53
    ри
    0.52
     खिलाड़ी
    0.52
    е
    0.52
    은
    0.52
    POSITIVE LOGITS
    Spend
    0.61
    راہیم
    0.56
    OfDay
    0.55
     outlay
    0.55
    im
    0.55
     spend
    0.55
    ,
    0.55
     marché
    0.54
     spree
    0.54
     süre
    0.54
    Activations Density 0.027%

    No Known Activations