© 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. 34-GEMMASCOPE-RES-131K
    7. 54189
    Prev
    Next
    INDEX
    Explanations

    rote learning and school subjects

    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
    нцип
    -0.92
     exagger
    -0.84
    identes
    -0.82
     fascin
    -0.79
    ilers
    -0.75
    škai
    -0.74
    錨
    -0.74
    можно
    -0.73
    GeneratedCode
    -0.73
     biker
    -0.73
    POSITIVE LOGITS
     memor
    1.71
     rote
    1.62
    memor
    1.60
     Memor
    1.38
     memorize
    1.37
     facts
    1.30
     spoon
    1.27
     regurg
    1.27
    rote
    1.27
     MEMOR
    1.20
    Activations Density 0.021%

    No Known Activations