© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128631
    Prev
    Next
    INDEX
    Explanations

    government and legal 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
     Incluso
    -1.44
    双方
    -1.42
     Tamanho
    -1.35
     الشاشة
    -1.30
     from
    -1.28
    ⃨
    -1.25
     प्रोड
    -1.24
    ࣭
    -1.24
    =[];
    
    -1.24
    ();?>
    -1.23
    POSITIVE LOGITS
     السياس
    1.88
     الحكومة
    1.52
    べし
    1.42
     multicolore
    1.42
    ִּ
    1.42
     правительства
    1.39
     元素
    1.34
     étages
    1.32
    ּוֹ
    1.31
     FOTO
    1.30
    Activations Density 0.000%

    No Known Activations