© 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. 40-GEMMASCOPE-2-RES-262K
    7. 10886
    Prev
    Next
    INDEX
    Explanations

    ability and proficiency

    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_40_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
    ёл
    0.41
     ആവശ്യ
    0.37
     necessitating
    0.36
    ⊥
    0.36
    kbeta
    0.35
    гъл
    0.34
    bolinks
    0.33
     አካ
    0.33
    ᒥ
    0.33
     مطابق
    0.33
    POSITIVE LOGITS
     ability
    1.69
     proficient
    1.68
     kemampuan
    1.66
    擅
    1.65
     adept
    1.62
     giỏi
    1.56
     способность
    1.55
    能力
    1.54
     excels
    1.53
     proficiency
    1.52
    Activations Density 0.075%

    No Known Activations