© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14520
    Prev
    Next
    INDEX
    Explanations

    homeschooling and school enrollment

    np_acts-logits-general · gemini-2.5-flash-lite

    homeschooling, enrollment, schools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_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
    씹
    0.40
    druck
    0.39
    fpr
    0.39
    publishing
    0.39
     fragrance
    0.38
    stahl
    0.38
     comical
    0.38
     धर्मशाला
    0.38
    菅
    0.38
     ದೇಹ
    0.37
    POSITIVE LOGITS
     homeschooling
    0.75
     homeschool
    0.69
     enrollment
    0.68
     enroll
    0.66
     enrol
    0.64
     Enroll
    0.63
     enrolment
    0.63
     enrolling
    0.60
     Enrollment
    0.60
     гимна
    0.55
    Activations Density 0.215%

    No Known Activations