© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67908
    Prev
    Next
    INDEX
    Explanations

    programming keywords return and var

    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
    たまた
    -2.33
    齮
    -2.28
    ⌵
    -2.19
    actéristi
    -2.05
    泚
    -2.00
     oplossing
    -1.99
     podkre
    -1.98
     accesorio
    -1.95
     vijf
    -1.93
    
    -1.93
    POSITIVE LOGITS
    “
    2.64
    :
    2.44
    ↵
    2.16
     have
    2.09
    .”
    2.09
     Some
    2.08
     by
    2.02
     on
    1.98
     Those
    1.97
     für
    1.91
    Activations Density 0.002%

    No Known Activations