© 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. 66655
    Prev
    Next
    INDEX
    Explanations

    Raj followed by mund

    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
    .
    -1.67
    ).
    -1.64
    ctober
    -1.60
    ():
    -1.54
    meuble
    -1.52
     would
    -1.48
    "):
    -1.47
    нав
    -1.45
    Sqft
    -1.44
     imprensa
    -1.41
    POSITIVE LOGITS
    笮
    1.73
    たまに
    1.72
     étan
    1.66
    出発
    1.57
     énorme
    1.56
    ℡
    1.55
    時々
    1.52
     accél
    1.51
     detayl
    1.50
    だいたい
    1.49
    Activations Density 0.000%

    No Known Activations