© 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. 34-GEMMASCOPE-RES-131K
    7. 54306
    Prev
    Next
    INDEX
    Explanations

    while + concurrent action

    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_34/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
     galite
    -1.07
     persino
    -1.06
     dokonce
    -1.05
     simply
    -1.04
     addirittura
    -1.04
     навіть
    -1.03
     idr
    -1.02
    сай
    -1.02
     アレンジ
    -1.01
     forskellige
    -1.00
    POSITIVE LOGITS
     also
    3.28
     still
    3.00
     simultaneously
    2.80
     jednocześnie
    2.61
     vẫn
    2.58
     gleichzeitig
    2.30
     também
    2.25
     tetap
    2.23
     Simultaneously
    2.22
     también
    2.16
    Activations Density 0.074%

    No Known Activations