© 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. 70507
    Prev
    Next
    INDEX
    Explanations

    school and children's learning experiences

    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
    ଶ
    -1.73
     mengumumkan
    -1.28
    ଵ
    -1.26
     суток
    -1.25
    🧤
    -1.20
     terrasse
    -1.20
    /}.
    -1.20
     milliard
    -1.19
     hôtel
    -1.17
     interieur
    -1.16
    POSITIVE LOGITS
     children
    1.51
     they
    1.45
     my
    1.39
     staff
    1.37
     learning
    1.33
    myspace
    1.30
     management
    1.29
     family
    1.27
     school
    1.27
     our
    1.27
    Activations Density 0.002%

    No Known Activations