© 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. 34-GEMMASCOPE-RES-131K
    7. 103374
    Prev
    Next
    INDEX
    Explanations

    direction

    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_34/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
     flexibilidad
    -1.22
    dentro
    -1.20
    ここで
    -1.10
    vator
    -1.03
     compresión
    -1.00
     ventilación
    -1.00
    üstet
    -0.98
     durabilidad
    -0.98
    Inside
    -0.96
     sostenibilidad
    -0.96
    POSITIVE LOGITS
     in
    4.97
     towards
    1.59
     în
    1.41
     åt
    1.40
     toward
    1.38
     In
    1.38
     في
    1.35
    的方向
    1.35
     direction
    1.29
     در
    1.24
    Activations Density 0.056%

    No Known Activations