© 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. 1832
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    _
    -1.52
    階級
    -1.27
     efectuar
    -1.20
    -
    -1.20
     často
    -1.19
     answer
    -1.18
     work
    -1.16
     website
    -1.15
     empleos
    -1.14
    ля
    -1.12
    POSITIVE LOGITS
     bijvoorbeeld
    1.70
     ANCHE
    1.40
    つづく
    1.37
    সূ
    1.36
     Ahora
    1.36
    octobre
    1.34
     например
    1.34
     대해
    1.33
     of
    1.32
    :\\
    1.30
    Activations Density 0.241%

    No Known Activations