© 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. 104763
    Prev
    Next
    INDEX
    Explanations

    reports that

    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
     всегда
    -1.20
    我们
    -1.17
     our
    -1.14
     мы
    -1.10
     truncation
    -1.09
    我們
    -1.05
     ما
    -1.03
    でしたね
    -1.02
     Poco
    -1.02
    ラックス
    -1.02
    POSITIVE LOGITS
     that
    1.48
     there
    1.31
    氳
    1.14
    ַּ
    1.09
    ówki
    1.09
     the
    1.07
     fraiche
    1.05
    さは
    1.04
     épices
    1.02
    ֵּ
    1.01
    Activations Density 0.040%

    No Known Activations