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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15101
    Prev
    Next
    INDEX
    Explanations

    say "m" words

    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
    ofSeconds
    0.55
    煩
    0.55
     إدارة
    0.55
    डीएम
    0.54
    ຢ
    0.53
     astronom
    0.52
     फार्म
    0.52
     управление
    0.52
     ইঞ্চি
    0.51
    टीएम
    0.51
    POSITIVE LOGITS
     Μ
    1.53
     m
    1.41
    Μ
    1.35
     mə
    1.19
     М
    1.16
     м
    1.15
     מ
    1.15
     ม
    1.15
    Ｍ
    1.13
     ma
    1.11
    Activations Density 0.683%

    No Known Activations