© 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. 90280
    Prev
    Next
    INDEX
    Explanations

    Dynastic names, dynos, names

    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
    注意事
    -3.05
    .''
    -2.77
    薆
    -2.63
    袮
    -2.56
    勠
    -2.38
     heo
    -2.34
     ¨
    -2.34
    }$
    -2.34
     questionSearch
    -2.28
     dafs
    -2.27
    POSITIVE LOGITS
     signifikan
    3.00
     It
    2.73
    骉
    2.56
    となりました
    2.38
     klarer
    2.36
     bekämp
    2.36
    ſelf
    2.34
     şi
    2.28
    になりますが
    2.28
     でも
    2.27
    Activations Density 0.005%

    No Known Activations