© 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. 22-GEMMASCOPE-RES-131K
    7. 39664
    Prev
    Next
    INDEX
    Explanations

    code-related keywords

    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
     tett
    -1.27
     岁
    -1.10
     even
    -1.09
    報酬
    -1.02
     because
    -1.02
     bolster
    -1.01
     more
    -0.98
    ⛲
    -0.98
    ilités
    -0.98
    katkan
    -0.98
    POSITIVE LOGITS
    _
    1.23
     &
    1.12
    &
    1.11
     basados
    1.09
     VERY
    1.09
    了自己
    1.09
    completely
    1.02
     diseñados
    1.01
     DURING
    1.00
     küçük
    1.00
    Activations Density 0.034%

    No Known Activations