© 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. 38009
    Prev
    Next
    INDEX
    Explanations

    children's actions and speech

    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
    sex
    -0.94
     детства
    -0.90
    jug
    -0.85
     блу
    -0.85
    Med
    -0.85
     sexy
    -0.84
     your
    -0.84
    svg
    -0.84
    students
    -0.83
     codif
    -0.82
    POSITIVE LOGITS
     mommy
    1.58
     Mommy
    1.49
     preschool
    1.34
     daddy
    1.32
    Mommy
    1.30
     Daddy
    1.28
    mommy
    1.22
     toddler
    1.13
     Preschool
    1.12
    Daddy
    1.09
    Activations Density 0.088%

    No Known Activations