© 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. 28256
    Prev
    Next
    INDEX
    Explanations

    formal and official contexts

    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
     of
    -1.62
    </u>
    -1.13
     heut
    -1.00
     --->
    -0.96
     heed
    -0.94
    ツヤ
    -0.88
     или
    -0.84
    我们就
    -0.84
     dunque
    -0.82
    ulic
    -0.82
    POSITIVE LOGITS
     dispozici
    1.16
    ༵
    1.12
     dekol
    1.11
     luxus
    1.11
    鑽
    1.09
     mikina
    1.09
    usaha
    1.09
    Примечание
    1.08
     technik
    1.08
     câmera
    1.08
    Activations Density 0.089%

    No Known Activations