© 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. 16318
    Prev
    Next
    INDEX
    Explanations

    technical jargon

    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
     مي‌
    -1.05
     segreto
    -1.03
     امریک
    -1.02
    倜
    -0.99
    ่ะ
    -0.96
     beeintr
    -0.96
     Reſ
    -0.94
     verletzt
    -0.92
     conseguenze
    -0.91
    ִּ
    -0.90
    POSITIVE LOGITS
    щик
    1.05
    镂
    1.04
    𝕊
    1.01
     reais
    0.96
    呪術
    0.94
     «
    0.94
    鷺
    0.92
    ванні
    0.92
    
    0.91
    頷
    0.91
    Activations Density 0.090%

    No Known Activations