© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87141
    Prev
    Next
    INDEX
    Explanations

    work with activities

    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
     before
    -1.71
     if
    -1.58
    ก่อน
    -1.38
     gdyby
    -1.37
     but
    -1.32
     beiden
    -1.25
    も同じ
    -1.23
     igualmente
    -1.19
    纔
    -1.18
     могли
    -1.17
    POSITIVE LOGITS
     on
    1.70
     into
    1.38
    刄
    1.23
    </h5>
    1.23
     including
    1.23
    ⭑
    1.22
    lots
    1.20
    
    1.16
     процесс
    1.16
    ⩕
    1.15
    Activations Density 0.100%

    No Known Activations