© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148049
    Prev
    Next
    INDEX
    Explanations

    kilowatt, Watt, and kWh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     inverno
    0.77
     વ
    0.77
     वा
    0.72
     vowels
    0.70
     circunferencia
    0.68
     Ма
    0.68
     Exptl
    0.68
     ન
    0.67
     diámetro
    0.66
     ۲۰۰
    0.66
    POSITIVE LOGITS
    age
    1.09
    ages
    0.98
    Hour
    0.95
     hour
    0.90
    agem
    0.89
    hour
    0.88
     hours
    0.86
    att
    0.86
     ساعت
    0.84
    েজ
    0.83
    Activations Density 0.007%

    No Known Activations