© 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-IT
    5. 41-GEMMASCOPE-2-RES-16K
    7. 7397
    Prev
    Next
    INDEX
    Explanations

    invading

    np_max-act-logits · gemini-2.5-flash-lite

    foreign language words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_16k_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
     soddisf
    0.52
    モチ
    0.51
    薰
    0.50
     poter
    0.49
    满意
    0.49
     satisfaction
    0.48
     satisfait
    0.48
    栄
    0.48
     тях
    0.48
     výrob
    0.47
    POSITIVE LOGITS
     adicionales
    0.73
     дополнительные
    0.72
     Zusatz
    0.72
     Bahasa
    0.71
     escritos
    0.70
     пишет
    0.68
     translators
    0.68
     добавля
    0.67
    жный
    0.67
     concaten
    0.66
    Activations Density 0.002%

    No Known Activations