© 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. 22-GEMMASCOPE-RES-131K
    4. 9549
    Prev
    Next
    INDEX
    Explanations

    city and street addresses

    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
     toh
    -1.12
    orithm
    -1.10
    ренд
    -1.03
    ₅
    -1.03
    🤬
    -1.02
    ojo
    -0.99
     only
    -0.99
     while
    -0.98
    AfterViewInit
    -0.97
    😗
    -0.97
    POSITIVE LOGITS
    私たちの
    1.23
    拍了拍
    1.10
    我覺得
    1.08
    diğ
    1.04
    抬起头
    1.02
    看來
    1.00
     поможет
    1.00
    Our
    0.97
    ждают
    0.96
    我们需要
    0.94
    Activations Density 0.004%

    No Known Activations