© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9493
    Prev
    Next
    INDEX
    Explanations

    countless followed by diverse nouns

    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_10/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
    鉭
    -2.31
    ↵↵
    -2.06
     essenti
    -2.06
     když
    -2.02
     金属
    -1.99
     Concerns
    -1.98
    Suka
    -1.98
     moléculas
    -1.98
    ꦫ
    -1.97
     escribiendo
    -1.95
    POSITIVE LOGITS
    ti
    2.48
    an
    2.48
    ࿚
    2.47
     ehemalige
    2.42
     ältere
    2.41
    縯
    2.31
    
    2.27
    ⏤
    2.20
     ทั้ง
    2.19
     Houſe
    2.19
    Activations Density 0.002%

    No Known Activations