© 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. 61340
    Prev
    Next
    INDEX
    Explanations

    detecting dates or date-related metadata

    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
    reale
    -1.26
     знаете
    -1.20
    świet
    -1.18
     dasselbe
    -1.17
     jederzeit
    -1.16
     anvä
    -1.14
    encyclo
    -1.14
    見た
    -1.14
    teve
    -1.14
     soportes
    -1.13
    POSITIVE LOGITS
     by
    1.25
     mentre
    1.23
     there
    1.10
    =@"
    1.07
    ternut
    1.07
     perquè
    1.07
     that
    1.04
    Materiál
    1.04
    romeda
    1.03
     mientras
    1.02
    Activations Density 0.252%

    No Known Activations