© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33621
    Prev
    Next
    INDEX
    Explanations

    n and words ending in ão, ões

    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_34/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
    fitrión
    -0.85
    時間は
    -0.77
     berätt
    -0.75
     Tent
    -0.75
    を
    -0.75
     sota
    -0.73
    週
    -0.73
    +};
    -0.72
     часть
    -0.72
     Ela
    -0.72
    POSITIVE LOGITS
    tory
    0.83
     knot
    0.75
    わけではない
    0.75
    вят
    0.74
    のではなく
    0.73
     américains
    0.73
    ㎜
    0.73
    ρισσότε
    0.73
    oneofs
    0.73
    interpretation
    0.72
    Activations Density 0.025%

    No Known Activations