© 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. 14594
    Prev
    Next
    INDEX
    Explanations

    teacher

    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
     aluminum
    0.59
     Aluminum
    0.56
    Aluminum
    0.55
    铝
    0.55
    serializing
    0.54
     алюми
    0.54
     genome
    0.54
    鋁
    0.53
     aluminio
    0.52
    aluminum
    0.52
    POSITIVE LOGITS
     teacher
    5.19
     teachers
    4.97
     Teacher
    4.88
    teacher
    4.81
    Teacher
    4.78
     Teachers
    4.72
    Teachers
    4.69
    teachers
    4.56
    老师
    4.50
    教师
    4.47
    Activations Density 0.185%

    No Known Activations