© 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. 9738
    Prev
    Next
    INDEX
    Explanations

    under specific laws or rules

    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
    そして
    -1.38
    íaco
    -1.30
    ⤴
    -1.28
    𨧀
    -1.27
     juc
    -1.27
     bagaimana
    -1.27
    保育
    -1.24
    ┖
    -1.23
    ņi
    -1.23
    ympto
    -1.23
    POSITIVE LOGITS
     the
    1.86
     terms
    1.59
     previous
    1.45
     United
    1.37
     different
    1.34
     defined
    1.33
     With
    1.32
    ホント
    1.30
     given
    1.27
     circumstances
    1.27
    Activations Density 0.033%

    No Known Activations