© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 169
    Prev
    Next
    INDEX
    Explanations

    code includes and namespaces

    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_22/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
     związane
    -0.98
     reú
    -0.95
     majeurs
    -0.93
     Wür
    -0.91
     postępo
    -0.90
     nanti
    -0.90
     zgodnie
    -0.90
     meleg
    -0.89
     сорта
    -0.88
    Слайд
    -0.88
    POSITIVE LOGITS
     and
    1.05
    punkten
    0.88
    эффици
    0.87
    verlust
    0.85
    limited
    0.85
     miseria
    0.85
    ical
    0.84
    ِّ
    0.84
    そういった
    0.84
     Webseiten
    0.84
    Activations Density 0.019%

    No Known Activations