© 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. 10-GEMMASCOPE-RES-131K
    4. 105377
    Prev
    Next
    INDEX
    Explanations

    signing players or deals

    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
     outros
    -1.69
     otros
    -1.53
     mxArray
    -1.42
     autres
    -1.36
     ello
    -1.30
     subje
    -1.28
    ๔
    -1.27
    : 
    -1.24
    咔嚓
    -1.24
    Работа
    -1.23
    POSITIVE LOGITS
     '';
    1.36
     brachten
    1.30
     such
    1.30
    簠
    1.28
     eivät
    1.27
     indivíduos
    1.25
    "/>
    1.25
    melle
    1.23
    şağı
    1.23
     YEARS
    1.22
    Activations Density 0.030%

    No Known Activations