© 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. 95782
    Prev
    Next
    INDEX
    Explanations

    museum complex

    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
     или
    -2.38
     /
    -2.28
    7
    -2.14
     это
    -2.14
     не
    -2.13
     WHAT
    -2.06
    泐
    -2.05
     VERY
    -2.00
     ใน
    -1.98
     {'
    -1.98
    POSITIVE LOGITS
    Ꮵ
    2.69
    庒
    2.64
    ’，
    2.38
    ዡ
    2.30
     bono
    2.30
     墊
    2.30
     MUSEUM
    2.19
    鹬
    2.17
    </strong>
    2.13
    .
    2.11
    Activations Density 0.013%

    No Known Activations