© 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. 87159
    Prev
    Next
    INDEX
    Explanations

    hashtags

    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
    鉝
    -2.25
    濑
    -2.20
    极了
    -2.19
    的吗
    -2.17
     validés
    -2.16
     albeit
    -2.16
     дуже
    -2.16
    criar
    -2.13
    ꯸
    -2.13
     admired
    -2.11
    POSITIVE LOGITS
     “
    2.41
     focussing
    2.11
     Then
    2.03
     периода
    2.03
     &
    1.98
     mange
    1.96
     registró
    1.95
    other
    1.95
     viviendo
    1.92
     OTHER
    1.89
    Activations Density 0.001%

    No Known Activations