© 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. 71504
    Prev
    Next
    INDEX
    Explanations

    specific entities and their associates

    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
    の人に
    -1.31
     anoche
    -1.22
    tatuaje
    -1.18
     PÅ
    -1.18
    なんですよ
    -1.17
    ytu
    -1.17
    cartão
    -1.16
     Czę
    -1.13
    なんですね
    -1.13
    感じが
    -1.13
    POSITIVE LOGITS
    ฯ
    1.99
    p
    1.29
    ot
    1.29
    ckeye
    1.27
    	
    1.24
    not
    1.23
    an
    1.21
    op
    1.20
     различные
    1.20
    ko
    1.19
    Activations Density 0.081%

    No Known Activations