© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8974
    Prev
    Next
    INDEX
    Explanations

    pyspark dataframe manipulation

    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
     We
    -1.51
     cheerfully
    -1.31
     we
    -1.26
    ⚋
    -1.21
     baseado
    -1.20
     propres
    -1.19
     \
    -1.18
     tion
    -1.17
     cópia
    -1.16
    が違う
    -1.15
    POSITIVE LOGITS
    瑒
    1.38
    création
    1.33
     swaps
    1.27
     vůbec
    1.25
    }$_
    1.21
    年も
    1.17
     Unglück
    1.16
     pokra
    1.16
     Verfü
    1.15
     nommée
    1.14
    Activations Density 0.029%

    No Known Activations