© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60240
    Prev
    Next
    INDEX
    Explanations

    names like Irene and Emil

    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
     erwähnten
    -3.36
     üblichen
    -3.28
     verwendeten
    -3.17
     gewünschten
    -2.77
     gesuchten
    -2.77
     angegebenen
    -2.69
    ldots
    -2.56
     факторов
    -2.48
    </b>
    -2.47
     betreffenden
    -2.44
    POSITIVE LOGITS
    ization
    3.22
    ção
    2.73
    ции
    2.69
    </h3>
    2.66
    隳
    2.53
     australiano
    2.50
    趼
    2.44
     dibujado
    2.42
    鶺
    2.36
    
    2.34
    Activations Density 0.002%

    No Known Activations