© 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. 41-GEMMASCOPE-2-RES-65K
    7. 15544
    Prev
    Next
    INDEX
    Explanations

    computing context

    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
    Dick
    0.57
    국의
    0.56
    Ɗ
    0.56
    Bo
    0.55
    Kep
    0.55
    コミ
    0.53
    Ga
    0.52
     सेवाओं
    0.52
    cieron
    0.52
    孅
    0.52
    POSITIVE LOGITS
     నో
    0.55
     সংশ
    0.54
     regenerated
    0.52
     erneut
    0.52
     lanjut
    0.51
     उदार
    0.50
     gọi
    0.50
     tls
    0.50
     nă
    0.50
     buradan
    0.50
    Activations Density 0.000%

    No Known Activations