© 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. 165581
    Prev
    Next
    INDEX
    Explanations

    quality, professional, household

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

    supply chains and logistics

    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
    0.56
     ピン
    0.50
     २४
    0.45
     BALL
    0.45
    """"
    0.44
     верну
    0.44
     た
    0.43
    ?“
    0.43
     斜
    0.43
     PIN
    0.43
    POSITIVE LOGITS
    ცხ
    0.48
    ر
    0.47
    designs
    0.45
     soviet
    0.45
     خانہ
    0.45
     હાઉસ
    0.44
     الأول
    0.44
    ια
    0.43
    household
    0.43
     Household
    0.43
    Activations Density 0.000%

    No Known Activations