© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93270
    Prev
    Next
    INDEX
    Explanations

    school and students

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     datter
    -0.84
    niť
    -0.77
     publicação
    -0.77
     zet
    -0.76
     herv
    -0.75
    女性
    -0.75
     Riproduzione
    -0.74
     আ
    -0.73
    存于
    -0.73
     der
    -0.72
    POSITIVE LOGITS
     students
    1.55
     school
    1.54
     teacher
    1.40
     boys
    1.37
     teachers
    1.16
    haviours
    1.13
     worksheet
    1.11
     student
    1.05
     soccer
    1.03
     approu
    1.03
    Activations Density 0.064%

    No Known Activations