© 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. 104776
    Prev
    Next
    INDEX
    Explanations

    time zone GMT

    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
     gelassen
    -2.25
     publicités
    -2.16
     blauen
    -2.09
    i
    -2.09
    sibirsk
    -2.00
    ocide
    -2.00
     magasins
    -1.99
    い
    -1.99
    يته
    -1.96
     beslu
    -1.96
    POSITIVE LOGITS
     Whether
    2.89
    剮
    2.34
     Choosing
    2.30
     Главная
    2.27
     effec
    2.23
     Become
    2.23
     decidedly
    2.20
     Therefore
    2.19
     define
    2.13
     Conversely
    2.11
    Activations Density 0.001%

    No Known Activations