© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57642
    Prev
    Next
    INDEX
    Explanations

    in phrases, prepositional phrases

    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
     zaradi
    -1.70
     hormigón
    -1.60
     flexibilidad
    -1.59
     ventilación
    -1.57
     compresión
    -1.55
     diámetro
    -1.51
     espesor
    -1.49
     cómodo
    -1.48
     ladrillo
    -1.46
     calefacción
    -1.45
    POSITIVE LOGITS
     in
    9.44
     في
    3.50
    ใน
    3.44
     In
    3.39
     در
    3.23
     dalam
    2.81
     във
    2.69
     katika
    2.64
    In
    2.56
     στην
    2.41
    Activations Density 0.279%

    No Known Activations