© 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. 73786
    Prev
    Next
    INDEX
    Explanations

    code components

    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
     マンガ
    -1.48
     コミック
    -1.48
     höl
    -1.43
     kompati
    -1.38
    samt
    -1.30
     хорошие
    -1.23
     kvalit
    -1.23
    っけ
    -1.21
     objekt
    -1.20
     vært
    -1.20
    POSITIVE LOGITS
    小孩子
    1.23
     quindi
    1.22
    的には
    1.21
    ställning
    1.16
     उसकी
    1.14
     Hinsicht
    1.12
     That
    1.10
     単
    1.08
    お気軽
    1.08
    medies
    1.06
    Activations Density 0.076%

    No Known Activations