© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 169878
    Prev
    Next
    INDEX
    Explanations

    competent, competence, competencies

    np_acts-logits-general · gemini-2.5-flash-lite

    competence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ا
    0.58
     Oreo
    0.55
     SoaException
    0.53
     extravaganza
    0.53
     Szk
    0.52
    كو
    0.52
     Bremen
    0.52
     Dik
    0.51
     കൂട്ട
    0.51
    م
    0.50
    POSITIVE LOGITS
    Compet
    0.95
     competency
    0.95
     competence
    0.92
     компет
    0.88
    compet
    0.86
     Compet
    0.86
     kompet
    0.84
     competent
    0.83
     компетен
    0.77
     compet
    0.75
    Activations Density 0.070%

    No Known Activations