© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3020
    Prev
    Next
    INDEX
    Explanations

    wheel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ların
    1.87
    film
    1.84
    finale
    1.82
    ่
    1.77
    т
    1.75
    า
    1.73
    ้
    1.69
    ции
    1.66
    nder
    1.65
    luss
    1.62
    POSITIVE LOGITS
    轳
    2.25
     wheels
    2.11
    barrow
    2.00
     rollerskates
    1.94
    ತ್ನ
    1.80
     มิถุนายน
    1.80
    𝘋
    1.73
    ƌ
    1.71
    ある
    1.70
     droplets
    1.70
    Activations Density 0.019%

    No Known Activations