© 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. 22-GEMMASCOPE-RES-131K
    7. 36023
    Prev
    Next
    INDEX
    Explanations

    components and contributions

    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
    arrivo
    -1.00
     usata
    -0.94
     получили
    -0.94
     seuil
    -0.93
    ViewChild
    -0.88
    の可能性
    -0.88
     recorte
    -0.87
     reposo
    -0.87
    憷
    -0.85
     presidencia
    -0.85
    POSITIVE LOGITS
     components
    1.03
    anteil
    1.01
     contributions
    1.01
     contribution
    1.00
    seit
    0.95
    层
    0.93
    EDIA
    0.93
     contribute
    0.91
     инструкция
    0.91
     component
    0.90
    Activations Density 0.120%

    No Known Activations