© 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. 104743
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "some"

    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
     некоторых
    -1.50
     取り付け
    -1.43
     facilidad
    -1.43
     nawet
    -1.39
     comodidad
    -1.38
     pantallas
    -1.37
     Ergänzung
    -1.33
     použit
    -1.33
    甚至
    -1.32
     EVEN
    -1.32
    POSITIVE LOGITS
     from
    2.59
     for
    1.78
     is
    1.62
     Since
    1.59
     at
    1.52
     Amazing
    1.45
     since
    1.43
    ttää
    1.41
     pukul
    1.41
     Only
    1.38
    Activations Density 0.037%

    No Known Activations