© 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. 10-GEMMASCOPE-RES-131K
    7. 47941
    Prev
    Next
    INDEX
    Explanations

    making permanent

    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_10/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
     \
    -1.29
    かず
    -1.26
     العالم
    -1.25
    AtIndexPath
    -1.20
     الجسم
    -1.20
    ぷら
    -1.17
    quisar
    -1.16
    Sudah
    -1.16
    Ontology
    -1.15
    ском
    -1.14
    POSITIVE LOGITS
     permanente
    1.58
    permanent
    1.45
     permanent
    1.38
    you
    1.38
     permanently
    1.34
     permanentes
    1.30
     on
    1.27
     enduring
    1.26
    永久
    1.25
     постоян
    1.24
    Activations Density 0.044%

    No Known Activations