© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73397
    Prev
    Next
    INDEX
    Explanations

    hex color codes

    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
    ּוֹ
    -1.55
    ַּ
    -1.28
    iç
    -1.19
     time
    -1.09
     歳
    -1.08
     deportivas
    -1.04
     тренер
    -0.98
    測試
    -0.98
    ִּ
    -0.96
    erobic
    -0.95
    POSITIVE LOGITS
    ׇ
    1.16
     hamp
    1.09
     Wartawan
    1.08
    kowa
    1.05
    oczes
    1.05
     jub
    1.04
     naturen
    1.02
    rids
    1.01
    搬
    0.98
    alogical
    0.96
    Activations Density 0.006%

    No Known Activations