© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13169
    Prev
    Next
    INDEX
    Explanations

    say "ed"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    ложение
    0.57
    ňa
    0.55
    oyi
    0.55
    ত্যা
    0.54
    ാരി
    0.54
    険
    0.54
    ondo
    0.52
    ዓ
    0.51
    imoto
    0.50
    uku
    0.50
    POSITIVE LOGITS
    ed
    3.39
    ted
    2.33
    ED
    2.25
    edLeft
    2.23
    ied
    2.17
    ned
    2.13
    edTest
    2.13
    ized
    2.08
    ged
    2.05
    ened
    2.03
    Activations Density 0.246%

    No Known Activations