© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 377
    Prev
    Next
    INDEX
    Explanations

    numbers containing the digit 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_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
     fittings
    0.78
    นาย
    0.77
     funerals
    0.76
     overseen
    0.76
     dõi
    0.74
    们
    0.72
    ция
    0.70
     memoirs
    0.70
    ای
    0.70
     ambulatory
    0.70
    POSITIVE LOGITS
    س
    0.97
    k
    0.89
    b
    0.84
    uit
    0.84
    g
    0.83
    েল
    0.82
    our
    0.82
    gak
    0.81
    kopf
    0.81
    z
    0.79
    Activations Density 0.630%

    No Known Activations