© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22152
    Prev
    Next
    INDEX
    Explanations

    non-English text prefixes

    np_acts-logits-general · gemini-2.5-flash-lite

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.50
    alarına
    0.48
    iella
    0.47
    ättning
    0.47
     prompted
    0.46
    pineapple
    0.46
    symbols
    0.46
    arla
    0.45
    ⽅
    0.44
    rano
    0.44
    POSITIVE LOGITS
     προσωπ
    0.45
    韻
    0.45
     পিছনে
    0.44
     ಹಿಂದೆ
    0.43
     अनुप्रयोग
    0.43
    ئت
    0.42
    偏移
    0.42
     একট
    0.42
     নেতৃত্বের
    0.41
    屜
    0.40
    Activations Density 0.000%

    No Known Activations