© 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. 66127
    Prev
    Next
    INDEX
    Explanations

    web browser drivers

    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
     versione
    -1.68
     as
    -1.62
     about
    -1.54
     actually
    -1.52
     during
    -1.49
     which
    -1.48
     equipe
    -1.48
     immediately
    -1.47
    ⢓
    -1.45
     of
    -1.43
    POSITIVE LOGITS
     sorgfäl
    1.63
     verfügb
    1.59
     budú
    1.58
     beinahe
    1.51
    Instead
    1.51
     hangout
    1.49
     représenter
    1.49
    ▰
    1.45
     verwendeten
    1.45
    ں
    1.45
    Activations Density 0.007%

    No Known Activations