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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93005
    Prev
    Next
    INDEX
    Explanations

    school and student contexts

    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_34/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
    Ŏ
    -0.95
    lenmiş
    -0.92
    świad
    -0.89
     piş
    -0.81
     géant
    -0.80
    CHM
    -0.79
     créativité
    -0.79
     vern
    -0.79
     keinginan
    -0.77
     Simpli
    -0.75
    POSITIVE LOGITS
     school
    2.30
     schools
    1.70
     students
    1.70
    school
    1.65
     student
    1.61
     School
    1.52
     шко
    1.43
    School
    1.36
     support
    1.32
     Student
    1.31
    Activations Density 0.036%

    No Known Activations